Showing papers in "The International Journal of Robotics Research in 2022"

Boreas: A multi-season autonomous driving dataset

Abstract: The Boreas dataset was collected by driving a repeated route over the course of 1 year, resulting in stark seasonal variations and adverse weather conditions such as rain and falling snow. In total, the Boreas dataset includes over 350 km of driving data featuring a 128-channel Velodyne Alpha-Prime lidar, a 360° Navtech CIR304-H scanning radar, a 5MP FLIR Blackfly S camera, and centimetre-accurate post-processed ground truth poses. Our dataset will support live leaderboards for odometry, metric localization, and 3D object detection. The dataset and development kit are available at boreas.utias.utoronto.ca.

Adaptively Informed Trees (AIT*) and Effort Informed Trees (EIT*): Asymmetric bidirectional sampling-based path planning

Abstract: Optimal path planning is the problem of finding a valid sequence of states between a start and goal that optimizes an objective. Informed path planning algorithms order their search with problem-specific knowledge expressed as heuristics and can be orders of magnitude more efficient than uninformed algorithms. Heuristics are most effective when they are both accurate and computationally inexpensive to evaluate, but these are often conflicting characteristics. This makes the selection of appropriate heuristics difficult for many problems. This paper presents two almost-surely asymptotically optimal sampling-based path planning algorithms to address this challenge, Adaptively Informed Trees (AIT*) and Effort Informed Trees (EIT*). These algorithms use an asymmetric bidirectional search in which both searches continuously inform each other. This allows AIT* and EIT* to improve planning performance by simultaneously calculating and exploiting increasingly accurate, problem-specific heuristics. The benefits of AIT* and EIT* relative to other sampling-based algorithms are demonstrated on 12 problems in abstract, robotic, and biomedical domains optimizing path length and obstacle clearance. The experiments show that AIT* and EIT* outperform other algorithms on problems optimizing obstacle clearance, where a priori cost heuristics are often ineffective, and still perform well on problems minimizing path length, where such heuristics are often effective.

Inducing structure in reward learning by learning features

Abstract: Reward learning enables robots to learn adaptable behaviors from human input. Traditional methods model the reward as a linear function of hand-crafted features, but that requires specifying all the relevant features a priori, which is impossible for real-world tasks. To get around this issue, recent deep Inverse Reinforcement Learning (IRL) methods learn rewards directly from the raw state but this is challenging because the robot has to implicitly learn the features that are important and how to combine them, simultaneously. Instead, we propose a divide-and-conquer approach: focus human input specifically on learning the features separately, and only then learn how to combine them into a reward. We introduce a novel type of human input for teaching features and an algorithm that utilizes it to learn complex features from the raw state space. The robot can then learn how to combine them into a reward using demonstrations, corrections, or other reward learning frameworks. We demonstrate our method in settings where all features have to be learned from scratch, as well as where some of the features are known. By first focusing human input specifically on the feature(s), our method decreases sample complexity and improves generalization of the learned reward over a deep IRL baseline. We show this in experiments with a physical 7-DoF robot manipulator, and in a user study conducted in a simulated environment.

RadarSLAM: A robust simultaneous localization and mapping system for all weather conditions

Abstract: A Simultaneous Localization and Mapping (SLAM) system must be robust to support long-term mobile vehicle and robot applications. However, camera and LiDAR based SLAM systems can be fragile when facing challenging illumination or weather conditions which degrade the utility of imagery and point cloud data. Radar, whose operating electromagnetic spectrum is less affected by environmental changes, is promising although its distinct sensor model and noise characteristics bring open challenges when being exploited for SLAM. This paper studies the use of a Frequency Modulated Continuous Wave radar for SLAM in large-scale outdoor environments. We propose a full radar SLAM system, including a novel radar motion estimation algorithm that leverages radar geometry for reliable feature tracking. It also optimally compensates motion distortion and estimates pose by joint optimization. Its loop closure component is designed to be simple yet efficient for radar imagery by capturing and exploiting structural information of the surrounding environment. Extensive experiments on three public radar datasets, ranging from city streets and residential areas to countryside and highways, show competitive accuracy and reliability performance of the proposed radar SLAM system compared to the state-of-the-art LiDAR, vision and radar methods. The results show that our system is technically viable in achieving reliable SLAM in extreme weather conditions on the RADIATE Dataset, for example, heavy snow and dense fog, demonstrating the promising potential of using radar for all-weather localization and mapping.

Offline motion libraries and online MPC for advanced mobility skills

Abstract: We describe an optimization-based framework to perform complex locomotion skills for robots with legs and wheels. The generation of complex motions over a long-time horizon often requires offline computation due to current computing constraints and is mostly accomplished through trajectory optimization (TO). In contrast, model predictive control (MPC) focuses on the online computation of trajectories, robust even in the presence of uncertainty, albeit mostly over shorter time horizons and is prone to generating nonoptimal solutions over the horizon of the task’s goals. Our article’s contributions overcome this trade-off by combining offline motion libraries and online MPC, uniting a complex, long-time horizon plan with reactive, short-time horizon solutions. We start from offline trajectories that can be, for example, generated by TO or sampling-based methods. Also, multiple offline trajectories can be composed out of a motion library into a single maneuver. We then use these offline trajectories as the cost for the online MPC, allowing us to smoothly blend between multiple composed motions even in the presence of discontinuous transitions. The MPC optimizes from the measured state, resulting in feedback control, which robustifies the task’s execution by reacting to disturbances and looking ahead at the offline trajectory. With our contribution, motion designers can choose their favorite method to iterate over behavior designs offline without tuning robot experiments, enabling them to author new behaviors rapidly. Our experiments demonstrate complex and dynamic motions on our traditional quadrupedal robot ANYmal and its roller-walking version. Moreover, the article’s findings contribute to evaluating five planning algorithms.

SVIn2: A multi-sensor fusion-based underwater SLAM system

Abstract: This paper presents SVIn2, a novel tightly-coupled keyframe-based Simultaneous Localization and Mapping (SLAM) system, which fuses Scanning Profiling Sonar, Visual, Inertial, and water-pressure information in a non-linear optimization framework for small and large scale challenging underwater environments. The developed real-time system features robust initialization, loop-closing, and relocalization capabilities, which make the system reliable in the presence of haze, blurriness, low light, and lighting variations, typically observed in underwater scenarios. Over the last decade, Visual-Inertial Odometry and SLAM systems have shown excellent performance for mobile robots in indoor and outdoor environments, but often fail underwater due to the inherent difficulties in such environments. Our approach combats the weaknesses of previous approaches by utilizing additional sensors and exploiting their complementary characteristics. In particular, we use (1) acoustic range information for improved reconstruction and localization, thanks to the reliable distance measurement; (2) depth information from water-pressure sensor for robust initialization, refining the scale, and assisting to limit the drift in the tightly-coupled integration. The developed software—made open source—has been successfully used to test and validate the proposed system in both benchmark datasets and numerous real world underwater scenarios, including datasets collected with a custom-made underwater sensor suite and an autonomous underwater vehicle Aqua2. SVIn2 demonstrated outstanding performance in terms of accuracy and robustness on those datasets and enabled other robotic tasks, for example, planning for underwater robots in presence of obstacles.

Versatile articulated aerial robot DRAGON: Aerial manipulation and grasping by vectorable thrust control

Abstract: Various state-of-the-art works have achieved aerial manipulation and grasping by attaching additional manipulator to aerial robots. However, such a coupled platform has limitations with respect to the interaction force and mobility. In this paper, we present the successful implementation of aerial manipulation and grasping by a novel articulated aerial robot called DRAGON, in which a vectorable rotor unit is embedded in each link. The key to performing stable manipulation and grasping in the air is the usage of rotor vectoring apparatus having two degrees-of-freedom. First, a comprehensive flight control methodology for aerial transformation using the vectorable thrust force is developed with the consideration of the dynamics of vectoring actuators. This proposed control method can suppress the oscillation due to the dynamics of vectoring actuators and also allow the integration with external and internal wrenches for object manipulation and grasping. Second, an online thrust-level planning method for bimanual object grasping using the two ends of this articulated model is presented. The proposed grasping style is unique in that the vectorable thrust force is used as the internal wrench instead of the joint torque. Finally, we show the experimental results of evaluation on the proposed control and planning methods for object manipulation and grasping.

Locally active globally stable dynamical systems: Theory, learning, and experiments

Abstract: State-dependent dynamical systems (DSs) offer adaptivity, reactivity, and robustness to perturbations in motion planning and physical human–robot interaction tasks. Learning DS-based motion plans from non-linear reference trajectories is an active research area in robotics. Most approaches focus on learning DSs that can (i) accurately mimic the demonstrated motion, while (ii) ensuring convergence to the target, i.e., they are globally asymptotically (or exponentially) stable. When subject to perturbations, a compliant robot guided with a DS will continue following the next integral curves of the DS towards the target. If the task requires the robot to track a specific reference trajectory, this approach will fail. To alleviate this shortcoming, we propose the locally active globally stable DS (LAGS-DS), a novel DS formulation that provides both global convergence and stiffness-like symmetric attraction behaviors around a reference trajectory in regions of the state space where trajectory tracking is important. This allows for a unified approach towards motion and impedance encoding in a single DS-based motion model, i.e., stiffness is embedded in the DS. To learn LAGS-DS from demonstrations we propose a learning strategy based on Bayesian non-parametric Gaussian mixture models, Gaussian processes, and a sequence of constrained optimization problems that ensure estimation of stable DS parameters via Lyapunov theory. We experimentally validated LAGS-DS on writing tasks with a KUKA LWR 4+ arm and on navigation and co-manipulation tasks with iCub humanoid robots.

GKNet: Grasp keypoint network for grasp candidates detection

Abstract: Contemporary grasp detection approaches employ deep learning to achieve robustness to sensor and object model uncertainty. The two dominant approaches design either grasp-quality scoring or anchor-based grasp recognition networks. This paper presents a different approach to grasp detection by treating it as keypoint detection in image-space. The deep network detects each grasp candidate as a pair of keypoints, convertible to the grasp representation g = { x, y, w, θ} T , rather than a triplet or quartet of corner points. Decreasing the detection difficulty by grouping keypoints into pairs boosts performance. To promote capturing dependencies between keypoints, a non-local module is incorporated into the network design. A final filtering strategy based on discrete and continuous orientation prediction removes false correspondences and further improves grasp detection performance. GKNet, the approach presented here, achieves a good balance between accuracy and speed on the Cornell and the abridged Jacquard datasets (96.9% and 98.39% at 41.67 and 23.26 fps). Follow-up experiments on a manipulator evaluate GKNet using four types of grasping experiments reflecting different nuisance sources: static grasping, dynamic grasping, grasping at varied camera angles, and bin picking. GKNet outperforms reference baselines in static and dynamic grasping experiments while showing robustness to varied camera viewpoints and moderate clutter. The results confirm the hypothesis that grasp keypoints are an effective output representation for deep grasp networks that provide robustness to expected nuisance factors.

ColoRadar: The direct 3D millimeter wave radar dataset

Abstract: This work presents two different forms of dense, high-resolution radar data from two frequency modulated continuous wave radar sensors, along sparse radar pointclouds produced by one of the radar sensors. In addition, all datasets include 3D lidar and inertial measurements, and a lidar-based simultaneous localization and mapping pose estimation. Over 2 h of 6D pose data was generated across 52 datasets collected in highly diverse 3D environments including lab spaces, outside and inside large buildings, urban walkways, and a mine. One dataset, from the ASPEN Lab, also includes precision groundtruth generated from a motion capture system. Intrinsic radar calibration and measured extrinsic sensor position calibrations are also provided along with python based development tools to interact with the various datasets. This data is designed to assist with generating radar based localization algorithms and calibrations between radar and other sensors.

Magnetic concentric tube robots: Introduction and analysis

Abstract: In this paper, we propose a new type of continuum robot, referred to as a magnetic concentric tube robot (M-CTR), for performing minimally invasive surgery in narrow and difficult-to-access areas. The robot combines concentric tubes and magnetic actuation to benefit from the ‘follow the leader’ behaviour, the dexterity and stability of existing robots, while targeting millimetre-sized external diameters. These three kinematic properties are assessed through numerical and experimental studies performed on a prototype of a M-CTR. They are performed with general forward and inverse kineto-static models of the robot, continuation and bifurcation analysis, and a specific experimental setup. The prototype presents unique capabilities in terms of deployment and active stability management, while its dexterity in terms of tip orientability is also among the best reported for other robots at its scale.

Hybrid control for combining model-based and model-free reinforcement learning

Abstract: We develop an approach to improve the learning capabilities of robotic systems by combining learned predictive models with experience-based state-action policy mappings. Predictive models provide an understanding of the task and the dynamics, while experience-based (model-free) policy mappings encode favorable actions that override planned actions. We refer to our approach of systematically combining model-based and model-free learning methods as hybrid learning. Our approach efficiently learns motor skills and improves the performance of predictive models and experience-based policies. Moreover, our approach enables policies (both model-based and model-free) to be updated using any off-policy reinforcement learning method. We derive a deterministic method of hybrid learning by optimally switching between learning modalities. We adapt our method to a stochastic variation that relaxes some of the key assumptions in the original derivation. Our deterministic and stochastic variations are tested on a variety of robot control benchmark tasks in simulation as well as a hardware manipulation task. We extend our approach for use with imitation learning methods, where experience is provided through demonstrations, and we test the expanded capability with a real-world pick-and-place task. The results show that our method is capable of improving the performance and sample efficiency of learning motor skills in a variety of experimental domains.

Automatic encoding and repair of reactive high-level tasks with learned abstract representations

Abstract: We present a framework for the automatic encoding and repair of high-level tasks. Given a set of skills a robot can perform, our approach first abstracts sensor data into symbols and then automatically encodes the robot’s capabilities in Linear Temporal Logic (LTL). Using this encoding, a user can specify reactive high-level tasks, for which we can automatically synthesize a strategy that executes on the robot, if the task is feasible. If a task is not feasible given the robot’s capabilities, we present two methods, one enumeration-based and one synthesis-based, for automatically suggesting additional skills for the robot or modifications to existing skills that would make the task feasible. We demonstrate our framework on a Baxter robot manipulating blocks on a table, a Baxter robot manipulating plates on a table, and a Kinova arm manipulating vials, with multiple sensor modalities, including raw images.

Method for generating real-time interactive virtual fixture for shared teleoperation in unknown environments

Abstract: A virtual fixture (VF) is a constraint built into software that assists a human operator in moving a remote tool along a preferred path via an augmented guidance force to improve teleoperation performance. However, teleoperation generally applies to unknown or dynamic environments, which are challenging for VF use. Most researchers have assumed that VFs are pre-defined or generated automatically; however, these processes are complicated and unreliable in unknown environments where teleoperation is in high demand. Recently, a few researchers have addressed this issue by introducing a user-interactive method of generating VFs in unknown environments. However, these methods are limited to generating a single type of primitive for a single robot tool. Moreover, the accuracy of the VF generated by these methods depends on the accuracy of the human input. Thus, applications of these methods are limited. To overcome those limitations, this work introduces a novel interactive VF generation method that includes a new method of representing VFs as a composition of components. A feature-based user interface allows the human operator to intuitively specify the VF components. The new VF representation accommodates a variety of robot tools and actions. Using the feature-based interface, the process of VF generation is more intuitive and accurate. In this study, the proposed method is evaluated with human subjects in three teleoperation experiments: peg-in-hole, pipe-sawing, and pipe-welding. The experimental results show that the VFs generated by the proposed approach result in a higher manipulation quality while demonstrating the lowest total workload in all experiments. The peg-in-hole task teleoperation was the safest in terms of failure proportion and exerted force of the robot tool. In the pipe-sawing task, the positioning of the robot tool was the most accurate. In the pipe-welding task, the quality of weld was the best in terms of measured tool-trajectory smoothness and visual weld observation.

Simplified decision making in the belief space using belief sparsification

Abstract: In this work, we introduce a new and efficient solution approach for the problem of decision making under uncertainty, which can be formulated as decision making in a belief space, over a possibly high-dimensional state space. Typically, to solve a decision problem, one should identify the optimal action from a set of candidates, according to some objective. We claim that one can often generate and solve an analogous yet simplified decision problem, which can be solved more efficiently. A wise simplification method can lead to the same action selection, or one for which the maximal loss in optimality can be guaranteed. Furthermore, such simplification is separated from the state inference and does not compromise its accuracy, as the selected action would finally be applied on the original state. First, we present the concept for general decision problems and provide a theoretical framework for a coherent formulation of the approach. We then practically apply these ideas to decision problems in the belief space, which can be simplified by considering a sparse approximation of their initial belief. The scalable belief sparsification algorithm we provide is able to yield solutions which are guaranteed to be consistent with the original problem. We demonstrate the benefits of the approach in the solution of a realistic active-SLAM problem and manage to significantly reduce computation time, with no loss in the quality of solution. This work is both fundamental and practical and holds numerous possible extensions.

BenchBot environments for active robotics (BEAR): Simulated data for active scene understanding research

Abstract: We present a platform to foster research in active scene understanding, consisting of high-fidelity simulated environments and a simple yet powerful API that controls a mobile robot in simulation and reality. In contrast to static, pre-recorded datasets that focus on the perception aspect of scene understanding, agency is a top priority in our work. We provide three levels of robot agency, allowing users to control a robot at varying levels of difficulty and realism. While the most basic level provides pre-defined trajectories and ground-truth localisation, the more realistic levels allow us to evaluate integrated behaviours comprising perception, navigation, exploration and SLAM. In contrast to existing simulation environments, we focus on robust scene understanding research using our environment interface (BenchBot) that provides a simple API for seamless transition between the simulated environments and real robotic platforms. We believe this scaffolded design is an effective approach to bridge the gap between classical static datasets without any agency and the unique challenges of robotic evaluation in reality. Our BenchBot Environments for Active Robotics (BEAR) consist of 25 indoor environments under day and night lighting conditions, a total of 1443 objects to be identified and mapped, and ground-truth 3D bounding boxes for use in evaluation. BEAR website: https://qcr.github.io/dataset/benchbot-bear-data/.

Control-oriented meta-learning

Abstract: Real-time adaptation is imperative to the control of robots operating in complex, dynamic environments. Adaptive control laws can endow even nonlinear systems with good trajectory tracking performance, provided that any uncertain dynamics terms are linearly parameterizable with known nonlinear features. However, it is often difficult to specify such features a priori, such as for aerodynamic disturbances on rotorcraft or interaction forces between a manipulator arm and various objects. In this paper, we turn to data-driven modeling with neural networks to learn, offline from past data, an adaptive controller with an internal parametric model of these nonlinear features. Our key insight is that we can better prepare the controller for deployment with control-oriented meta-learning of features in closed-loop simulation, rather than regression-oriented meta-learning of features to fit input-output data. Specifically, we meta-learn the adaptive controller with closed-loop tracking simulation as the base-learner and the average tracking error as the meta-objective. With both fully actuated and underactuated nonlinear planar rotorcraft subject to wind, we demonstrate that our adaptive controller outperforms other controllers trained with regression-oriented meta-learning when deployed in closed-loop for trajectory tracking control.

Continuum robot state estimation using Gaussian process regression on S E ( 3 )

Abstract: Continuum robots have the potential to enable new applications in medicine, inspection, and countless other areas due to their unique shape, compliance, and size. Excellent progress has been made in the mechanical design and dynamic modeling of continuum robots, to the point that there are some canonical designs, although new concepts continue to be explored. In this paper, we turn to the problem of state estimation for continuum robots that can been modeled with the common Cosserat rod model. Sensing for continuum robots might comprise external camera observations, embedded tracking coils, or strain gauges. We repurpose a Gaussian process (GP) regression approach to state estimation, initially developed for continuous-time trajectory estimation in SE(3). In our case, the continuous variable is not time but arclength and we show how to estimate the continuous shape (and strain) of the robot (along with associated uncertainties) given discrete, noisy measurements of both pose and strain along the length. We demonstrate our approach quantitatively through simulations as well as through experiments. Our evaluations show that accurate and continuous estimates of a continuum robot’s shape can be achieved, resulting in average end-effector errors between the estimated and ground truth shape as low as 3.5 mm and 0.016° in simulation or 3.3 mm and 0.035° for unloaded configurations and 6.2 mm and 0.041° for loaded ones during experiments, when using discrete pose measurements.

Passive and active acoustic sensing for soft pneumatic actuators

Abstract: We propose a sensorization method for soft pneumatic actuators that uses an embedded microphone and speaker to measure different actuator properties. The physical state of the actuator determines the specific modulation of sound as it travels through the structure. Using simple machine learning, we create a computational sensor that infers the corresponding state from sound recordings. We demonstrate the acoustic sensor on a soft pneumatic continuum actuator and use it to measure contact locations, contact forces, object materials, actuator inflation, and actuator temperature. We show that the sensor is reliable (average classification rate for six contact locations of 93%), precise (mean spatial accuracy of 3.7 mm), and robust against common disturbances like background noise. Finally, we compare different sounds and learning methods and achieve best results with 20 ms of white noise and a support vector classifier as the sensor model.

Rubik Tables and object rearrangement

Abstract: A great number of robotics applications demand the rearrangement of many mobile objects, for example, organizing products on store shelves, shuffling containers at shipping ports, reconfiguring fleets of mobile robots, and so on. To boost the efficiency/throughput in systems designed for solving these rearrangement problems, it is essential to minimize the number of atomic operations that are involved, for example, the pick-n-places of individual objects. However, this optimization task poses a rather difficult challenge due to the complex inter-dependency between the objects, especially when they are tightly packed together. In this work, in tackling the aforementioned challenges, we have developed a novel algorithmic tool, called Rubik Tables, that provides a clean abstraction of object rearrangement problems as the proxy problem of shuffling items stored in a table or lattice. In its basic form, a Rubik Table is an n × n table containing n 2 items. We show that the reconfiguration of items in such a Rubik Table can be achieved using at most n column and n row shuffles in the partially labeled setting, where each column (resp., row) shuffle may arbitrarily permute the items stored in a column (resp., row) of the table. When items are fully distinguishable, additional n shuffles are needed. Rubik Tables allow many generalizations, for example, adding an additional depth dimension or extending to higher dimensions. Using Rubik Table results, we have designed a first constant-factor optimal algorithm for stack rearrangement problems where items are stored in stacks, accessible only from the top. We show that, for nd items stored in n stacks of depth d each, using one empty stack as the swap space, O( nd) stack pop-push operations are sufficient for an arbitrary reconfiguration of the stacks where [Formula: see text] for arbitrary fixed m > 0. Rubik Table results also allow the development of constant-factor optimal solutions for solving multi-robot motion planning problems under extreme robot density. These algorithms based on Rubik Table results run in low-polynomial time.

The split-belt rimless wheel

Abstract: Split-belt treadmill walking, in which the two belts move at different speeds, reveals a mechanism through which energy can be extracted from the environment. When a person walks with positive step length asymmetry on a split-belt treadmill, the treadmill can perform net positive work on the person. Here we use a split-belt rimless wheel model to explore how people could take advantage of the treadmill. We show that a split-belt rimless wheel can passively walk steadily by capturing energy from the treadmill to overcome collision losses, whereas it loses energy on each step with no way to recover the losses when walking on tied belts. Our simulated split-belt rimless wheel can walk steadily for a variety of leg angle and belt speed combinations, tolerating both speed disturbances and ground height variability. The wheel can even capture enough energy to walk uphill. We also built a physical split-belt rimless wheel robot and demonstrated that it can walk continuously without additional energy input. In comparing the wheel solutions to human split-belt gait, we found that humans do not maximize positive work performed by the treadmill. Other aspects of walking, such as costs associated with swing, balance, and free vertical moments, likely limit people’s ability to benefit from the treadmill. This study uses a simple walking model to characterize the mechanics and energetics of split-belt walking, demonstrating that energy capture through intermittent contact with two belts is possible and providing a simple model framework for understanding human adaptation during split-belt walking.

AURORA, a multi-sensor dataset for robotic ocean exploration

Abstract: The current maturity of autonomous underwater vehicles (AUVs) has made their deployment practical and cost-effective, such that many scientific, industrial and military applications now include AUV operations. However, the logistical difficulties and high costs of operating at sea are still critical limiting factors in further technology development, the benchmarking of new techniques and the reproducibility of research results. To overcome this problem, this paper presents a freely available dataset suitable to test control, navigation, sensor processing algorithms and others tasks. This dataset combines AUV navigation data, sidescan sonar, multibeam echosounder data and seafloor camera image data, and associated sensor acquisition metadata to provide a detailed characterisation of surveys carried out by the National Oceanography Centre (NOC) in the Greater Haig Fras Marine Conservation Zone (MCZ) of the U.K in 2015.

The Before, During, and After of Multi-Robot Deadlock

Abstract: Collision avoidance for multi-robot systems is a well-studied problem. Recently, control barrier functions (CBFs) have been proposed for synthesizing controllers that guarantee collision avoidance and goal stabilization for multiple robots. However, it has been noted that reactive control synthesis methods (such as CBFs) are prone to deadlock, an equilibrium of system dynamics that causes the robots to stall before reaching their goals. In this paper, we analyze the closed-loop dynamics of robots using CBFs, to characterize controller parameters, initial conditions, and goal locations that invariably lead the system to deadlock. Using tools from duality theory, we derive geometric properties of robot configurations of an N robot system once it is in deadlock and we justify them using the mechanics interpretation of KKT conditions. Our key deductions are that (1) system deadlock is characterized by a force equilibrium on robots and (2) deadlock occurs to ensure safety when safety is at the brink of being violated. These deductions allow us to interpret deadlock as a subset of the state space, and we show that this set is non-empty and located on the boundary of the safe set. By exploiting these properties, we analyze the number of admissible robot configurations in deadlock and develop a provably correct decentralized algorithm for deadlock resolution to safely deliver the robots to their goals. This algorithm is validated in simulations as well as experimentally on Khepera-IV robots. For an interactive version of this paper, please visit https://tinyurl.com/229tpssp

Reactive task and motion planning for robust whole-body dynamic locomotion in constrained environments

Abstract: Contact-based decision and planning methods are becoming increasingly important to endow higher levels of autonomy for legged robots. Formal synthesis methods derived from symbolic systems have great potential for reasoning about high-level locomotion decisions and achieving complex maneuvering behaviors with correctness guarantees. This study takes a first step toward formally devising an architecture composed of task planning and control of whole-body dynamic locomotion behaviors in constrained and dynamically changing environments. At the high level, we formulate a two-player temporal logic game between the multi-limb locomotion planner and its dynamic environment to synthesize a winning strategy that delivers symbolic locomotion actions. These locomotion actions satisfy the desired high-level task specifications expressed in a fragment of temporal logic. Those actions are sent to a robust finite transition system that synthesizes a locomotion controller that fulfills state reachability constraints. This controller is further executed via a low-level motion planner that generates feasible locomotion trajectories. We construct a set of dynamic locomotion models for legged robots to serve as a template library for handling diverse environmental events. We devise a replanning strategy that takes into consideration sudden environmental changes or large state disturbances to increase the robustness of the resulting locomotion behaviors. We formally prove the correctness of the layered locomotion framework guaranteeing a robust implementation by the motion planning layer. Simulations of reactive locomotion behaviors in diverse environments indicate that our framework has the potential to serve as a theoretical foundation for intelligent locomotion behaviors.

Sequential contact-based adaptive grasping for robotic hands

Abstract: This paper proposes a novel type of grasping strategy that draws inspiration from the role of touch and the importance of wrist motions in human grasping. The proposed algorithm, which we call Sequential Contact-based Adaptive Grasping, can be used to reactively modify a given grasp plan according to contacts arising between the hand and the object. This technique, based on a systematic constraint categorization and an iterative task inversion procedure, is shown to lead to synchronized motions of the fingers and the wrist, as it can be observed in humans, and to increase grasp success rate by substantially mitigating the relevant problems of object slippage during hand closure and of uncertainties caused by the environment and by the perception system. After describing the grasping problem in its quasi-static aspects, the algorithm is derived and discussed with some simple simulations. The proposed method is general as it can be applied to different kinds of robotic hands. It refines a priori defined grasp plans and significantly reduces their accuracy requirements by relying only on a forward kinematic model and elementary contact information. The efficacy of our approach is confirmed by experimental results of tests performed on a collaborative robot manipulator equipped with a state-of-the-art underactuated soft hand.

Motion planning by learning the solution manifold in trajectory optimization

Abstract: The objective function used in trajectory optimization is often non-convex and can have an infinite set of local optima. In such cases, there are diverse solutions to perform a given task. Although there are a few methods to find multiple solutions for motion planning, they are limited to generating a finite set of solutions. To address this issue, we present an optimization method that learns an infinite set of solutions in trajectory optimization. In our framework, diverse solutions are obtained by learning latent representations of solutions. Our approach can be interpreted as training a deep generative model of collision-free trajectories for motion planning. The experimental results indicate that the trained model represents an infinite set of homotopic solutions for motion planning problems.

MassMIND: Massachusetts Maritime INfrared Dataset

Abstract: Recent advances in deep learning technology have triggered radical progress in the autonomy of ground vehicles. Marine coastal Autonomous Surface Vehicles (ASVs) that are regularly used for surveillance, monitoring, and other routine tasks can benefit from this autonomy. Long haul deep sea transportation activities are additional opportunities. These two use cases present very different terrains—the first being coastal waters—with many obstacles, structures, and human presence while the latter is mostly devoid of such obstacles. Variations in environmental conditions are common to both terrains. Robust labeled datasets mapping such terrains are crucial in improving the situational awareness that can drive autonomy. However, there are only limited such maritime datasets available and these primarily consist of optical images. Although, long wave infrared (LWIR) is a strong complement to the optical spectrum that helps in extreme light conditions, a labeled public dataset with LWIR images does not currently exist. In this paper, we fill this gap by presenting a labeled dataset of over 2900 LWIR segmented images captured in coastal maritime environment over a period of 2 years. The images are labeled using instance segmentation and classified into seven categories—sky, water, obstacle, living obstacle, bridge, self, and background. We also evaluate this dataset across three deep learning architectures (UNet, PSPNet, DeepLabv3) and provide detailed analysis of its efficacy. While the dataset focuses on the coastal terrain, it can equally help deep sea use cases. Such terrain would have less traffic, and the classifier trained on cluttered environment would be able to handle sparse scenes effectively. We share this dataset with the research community with the hope that it spurs new scene understanding capabilities in the maritime environment.

Hybrid sparse monocular visual odometry with online photometric calibration

Abstract: Most monocular visual Simultaneous Localization and Mapping (vSLAM) and visual odometry (VO) algorithms focus on either feature-based methods or direct methods. Hybrid (semi-direct) approach is less studied although it is equally important. In this paper, a hybrid sparse visual odometry (HSO) algorithm with online photometric calibration is proposed for monocular vision. HSO introduces two novel measures, that is, direct image alignment with adaptive mode selection and image photometric description using ratio factors, to enhance the robustness against dramatic image intensity changes and motion blur. Moreover, HSO is able to establish pose constraints between keyframes far apart in time and space by using KLT tracking enhanced with a local-global brightness consistency. The convergence speed of candidate map points is adopted as the basis for keyframe selection, which strengthens the coordination between the front end and the back end. Photometric calibration is elegantly integrated into the VO system working in tandem: (1) Photometric interference from the camera, such as vignetting and changes in exposure time, is accurately calibrated and compensated in HSO, thereby improving the accuracy and robustness of VO. (2) On the other hand, VO provides pre-calculated data for the photometric calibration algorithm, which reduces resource consumption and improves the estimation accuracy of photometric parameters. Extensive experiments are performed on various public datasets to evaluate the proposed HSO against the state-of-the-art monocular vSLAM/VO and online photometric calibration methods. The results show that the proposed HSO achieves superior performance on VO and photometric calibration in terms of accuracy, robustness, and efficiency, being comparable with the state-of-the-art VO/vSLAM systems. We open source HSO for the benefit of the community.

Joint search of optimal topology and trajectory for planar linkages

Abstract: We present an algorithm to compute planar linkage topology and geometry, given a user-specified end-effector trajectory. Planar linkage structures convert rotational or prismatic motions of a single actuator into an arbitrarily complex periodic motion, which is an important component when building low-cost, modular robots, mechanical toys, and foldable structures in our daily lives (chairs, bikes, and shelves). The design of such structures requires trial and error even for experienced engineers. Our research provides semi-automatic methods for exploring novel designs given high-level specifications and constraints. We formulate this problem as a non-smooth numerical optimization with quadratic objective functions and non-convex quadratic constraints involving mixed-integer decision variables (MIQCQP). We propose and compare three approximate algorithms to solve this problem: mixed-integer conic-programming (MICP), mixed-integer nonlinear programming (MINLP), and simulated annealing (SA). We evaluated these algorithms searching for planar linkages involving 10 − 14 rigid links. Our results show that the best performance can be achieved by combining MICP and MINLP, leading to a hybrid algorithm capable of finding the planar linkages within a couple of hours on a desktop machine, which significantly outperforms the SA baseline in terms of optimality. We highlight the effectiveness of our optimized planar linkages by using them as legs of a walking robot.

Planning to chronicle: Optimal policies for narrative observation of unpredictable events

Abstract: One important class of applications entails a robot scrutinizing, monitoring, or recording the evolution of an uncertain time-extended process. This sort of situation leads to an interesting family of active perception problems that can be cast as planning problems in which the robot is limited in what it sees and must, thus, choose what to pay attention to. The distinguishing characteristic of this setting is that the robot has influence over what it captures via its sensors, but exercises no causal authority over the process evolving in the world. As such, the robot’s objective is to observe the underlying process and to produce a “chronicle” of occurrent events, subject to a goal specification of the sorts of event sequences that may be of interest. This paper examines variants of such problems in which the robot aims to collect sets of observations to meet a rich specification of their sequential structure. We study this class of problems by modeling a stochastic process via a variant of a hidden Markov model and specify the event sequences of interest as a regular language, developing a vocabulary of “mutators” that enable sophisticated requirements to be expressed. Under different suppositions on the information gleaned about the event model, we formulate and solve different planning problems. The core underlying idea is the construction of a product between the event model and a specification automaton. Using this product, we compute a policy that minimizes the expected number of steps to reach a goal state. We introduce a general algorithm for this problem as well as several more efficient algorithms for important special cases. The paper reports and compares performance metrics by drawing on some small case studies analyzed in depth via simulation. Specifically, we study the effect of the robot’s observation model on the average time required for the robot to record a desired story. We also compare our algorithm with a baseline greedy algorithm, showing that our algorithm outperforms the greedy algorithm in terms of the average time to record a desired story. In addition, experiments show that the algorithms tailored to specialized variants of the problem are rather more efficient than the general algorithm.