Showing papers in "The International Journal of Robotics Research in 2020"
TL;DR: This work uses reinforcement learning (RL) to learn dexterous in-hand manipulation policies that can perform vision-based object reorientation on a physical Shadow Dexterous Hand, and these policies transfer to the physical robot despite being trained entirely in simulation.
Abstract: We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies that can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed...
1,428 citations
TL;DR: In this article, the ability of intelligent autonomous systems to perceive, understand, and anticipate human behavior becomes increasingly important in a growing number of intelligent systems in human environments, and the ability to do so is discussed.
Abstract: With growing numbers of intelligent autonomous systems in human environments, the ability of such systems to perceive, understand, and anticipate human behavior becomes increasingly important. Spec...
547 citations
TL;DR: A novel approach to perform object-independent grasp synthesis from depth images via deep neural networks overcomes shortcomings in existing techniques, namely discrete sampling of grasp candidates and long computation times, and achieves better performance, particularly in clutter.
Abstract: We present a novel approach to perform object-independent grasp synthesis from depth images via deep neural networks. Our generative grasping convolutional neural network (GG-CNN) predicts a pixel-...
225 citations
TL;DR: This work tackles for the first time the development of closed-loop dynamic controllers for a continuous soft robot and presents two architectures designed for dynamic trajectory tracking and surface following, respectively.
Abstract: Leveraging the elastic bodies of soft robots promises to enable the execution of dynamic motions as well as compliant and safe interaction with an unstructured environment. However, the exploitatio...
173 citations
TL;DR: A decentralized sensor-level collision-avoidance policy for multi-robot systems, which enables a robot to make effective progress in a crowd without getting stuck and has been successfully deployed on different types of physical robot platforms without tedious parameter tuning.
Abstract: Developing a safe and efficient collision-avoidance policy for multiple robots is challenging in the decentralized scenarios where each robot generates its paths with limited observation of other r...
170 citations
TL;DR: The Task-Oriented Grasping Network (TOG-Net) is proposed to jointly optimize both task-oriented grasping of a tool and the manipulation policy for that tool.
Abstract: Tool manipulation is vital for facilitating robots to complete challenging task goals. It requires reasoning about the desired effect of the task and, thus, properly grasping and manipulating the t...
158 citations
TL;DR: This work develops a contact-aided invariant extended Kalman filter (InEKF) using the theory of Lie groups and invariant observer design and demonstrates how to include IMU biases, add/remove contacts, and formulate both world-centric and robo-centric versions.
Abstract: Legged robots require knowledge of pose and velocity in order to maintain stability and execute walking paths. Current solutions either rely on vision data, which is susceptible to environmental an...
145 citations
TL;DR: SegMap is presented: a map representation solution for localization and mapping based on the extraction of segments in 3D point clouds that achieves a higher localization accuracy and a 6% increase in recall over state-of-the-art handcrafted descriptors.
Abstract: Precisely estimating a robot’s pose in a prior, global map is a fundamental capability for mobile robotics, e.g., autonomous driving or exploration in disaster zones. This task, however, remains ch...
124 citations
TL;DR: A method of controlling 2D static and time-varying formations among collective self-repelling ferromagnetic microrobots by spatially and temporally programming an external magnetic potential energy distribution at the air–water interface or on solid surfaces is presented.
Abstract: Magnetically actuated mobile microrobots can access distant, enclosed, and small spaces, such as inside microfluidic channels and the human body, making them appealing for minimally invasive tasks....
117 citations
TL;DR: This work presents an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost on-board sensors and shows that policies trained with online imitation learning overcome well-known challenges related to covariate shift and generalize better than policiestrained with batch imitation learning.
Abstract: We present an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost on-board sensors. By imitating a model predictive controller equipped with advanced sen...
98 citations
TL;DR: This work proposes that the robot should use the model’s current predictive accuracy to inform the degree of confidence in its future predictions, and generates probabilistic motion predictions that exploit modeled structure when the structure successfully explains human motion, and degrade gracefully whenever the human moves unexpectedly.
Abstract: One of the most difficult challenges in robot motion planning is to account for the behavior of other moving agents, such as humans. Commonly, practitioners employ predictive models to reason about...
TL;DR: A novel variable stiffness mechanism powered by a set of embedded Shape Memory Alloy (SMA) springs, which can make the drive rods become ‘locked’ on the body structure with different configurations, and can exhibit an S-shaped curve when subject to single-directional forces is presented.
Abstract: Continuum robots exhibit promising adaptability and dexterity for soft manipulation due to their intrinsic compliance. However, this compliance may lead to challenges in modeling as well as positio...
TL;DR: A minimally interventional safety controller operating within an autonomous vehicle control stack with the role of ensuring collision-free interaction with an externally controlled counterpart while respecting static obstacles such as a road boundary wall is introduced.
Abstract: Action anticipation, intent prediction, and proactive behavior are all desirable characteristics for autonomous driving policies in interactive scenarios. Paramount, however, is ensuring safety on ...
TL;DR: In this article, a new highly scalable and asymptotically optimal control synthesis algorithm from linear temporal logic specifications, called STyLuS* for large-scale optimal Temporal Logic S...
Abstract: This article proposes a new highly scalable and asymptotically optimal control synthesis algorithm from linear temporal logic specifications, called STyLuS* for large-Scale optimal Temporal Logic S...
TL;DR: Path planning in robotics often requires finding high-quality solutions to continuously valued and/or high-dimensional problems as mentioned in this paper, and most planning algorithms instead focus on finding high quality solutions to high dimensional problems.
Abstract: Path planning in robotics often requires finding high-quality solutions to continuously valued and/or high-dimensional problems. These problems are challenging and most planning algorithms instead ...
TL;DR: This work aims to deploy localization at a global scale where one thus relies on methods using local features and sparse 3D models using a combination of priors, nearest-neighbor search, geometric match culling, and a cascaded pose candidate refinement step.
Abstract: The overarching goals in image-based localization are scale, robustness, and speed. In recent years, approaches based on local features and sparse 3D point-cloud models have both dominated the benc...
TL;DR: A challenging multi-agent seasonal dataset collected by a fleet of Ford autonomous vehicles (AVs) at different days and times during 2017–2018 that can help design robust algorithms for AVs and multi- agent systems is presented.
Abstract: This article presents a challenging multi-agent seasonal dataset collected by a fleet of Ford autonomous vehicles (AVs) at different days and times during 2017–2018. The vehicles traversed an avera...
TL;DR: INGRESS, a robot system that follows human natural language instructions to pick and place everyday objects, is presented and a two-stage neural-network model for grounding is proposed and outperformed a state-of-the-art method on the RefCOCO dataset and in robot experiments with humans.
Abstract: This article presents INGRESS, a robot system that follows human natural language instructions to pick and place everyday objects. The key question here is to ground referring expressions: understa...
TL;DR: In this paper, autonomous robots use a receding-horizon strategy to plan trajectories, wherein they execute a short plan while creating the n-directional map of the environment.
Abstract: To operate with limited sensor horizons in unpredictable environments, autonomous robots use a receding-horizon strategy to plan trajectories, wherein they execute a short plan while creating the n...
TL;DR: This work confirms that antipodal grasps are more stable when contact with the object occurs on the side of the fingers, and shows that higher-quality precision grasping is achieved through pinch grasping via fingers with the proximally actuated finger design compared to uniformly actuated fingers.
Abstract: In this work, we discuss the design of soft robotic fingers for robust precision grasping. Through a conceptual analysis of the finger shape and compliance during grasping, we confirm that antipoda...
TL;DR: The design and characterization of a soft gripper with an active palm to control grasp postures is presented and a computational finite-element model is proposed to predict finger kinematics.
Abstract: The design and characterization of a soft gripper with an active palm to control grasp postures is presented herein. The gripper structure is a hybrid of soft and stiff components to facilitate int...
TL;DR: The Model Predictive Controller with Learned Mode Scheduling (MPC-LMS) is introduced, which leverages integer programming and machine learning techniques to effectively deal with the combinatorial complexity associated with determining sequences of contact modes.
Abstract: This article presents an offline solution and online approximation to the hybrid control problem of planar non-prehensile manipulation. Hybrid dynamics and underactuation are key characteristics of...
TL;DR: Conducting formal verification (model checking), simulation-based testing, and user validation in experiments with a real robot allows V&V of the human–robot interaction task at different levels of modeling detail and thoroughness of exploration, thus overcoming the individual limitations of each technique.
Abstract: We present an approach for the verification and validation (V&V) of robot assistants in the context of human–robot interactions, to demonstrate their trustworthiness through corroborative evidence ...
TL;DR: Body posture influences human and robot performance in manipulation tasks, as appropriate poses facilitate motion or the exertion of force along different axes as mentioned in this paper. But, body posture does not directly affect robot performance.
Abstract: Body posture influences human and robot performance in manipulation tasks, as appropriate poses facilitate motion or the exertion of force along different axes. In robotics, manipulability ellipsoi...
TL;DR: This article proposes the use of interpenetrating phase composites (IPCs) materials with mathematically generated topologies based on triply periodic minimal surfaces for the development of soft grippers with desired mechanical properties and shows that by properly regulating the properties of IPCs material it is possible to design modular gripper structures with different closure motions.
Abstract: Advances in soft robotics and material science have enabled rapid progress in soft grippers. The ability to 3D print materials with softer, more elastic materials properties is a recent development...
TL;DR: This article provides a complete, self-contained, tutorial derivation of the relative Kalman filter, which has been thoroughly motivated but only briefly described to date, and derives the filter both for traditional dynamics defined with respect to an inertial frame, and for robocentric dynamics definedwith respect to the vehicle’s body frame.
Abstract: This work presents a multiplicative extended Kalman filter (MEKF) for estimating the relative state of a multirotor vehicle operating in a GPS-denied environment. The filter fuses data from an iner...
TL;DR: The mechanics and algorithms to compute the set of feasible motions of an object pushed in a plane, known as the motion cone, are presented and their use for the dynamic propagation step in a sampling-based planning algorithm is demonstrated.
Abstract: In this article, we present the mechanics and algorithms to compute the set of feasible motions of an object pushed in a plane. This set is known as the motion cone and was previously described for...
TL;DR: A human-subject study of two distinct task domains of a Fetch robot performing household tasks and a virtual reality simulation of an autonomous vehicle performing driving and parking maneuvers suggests that task-dependent functional trust models capture human trust in robot capabilities more accurately and trust transfer across tasks can be inferred to a good degree.
Abstract: Trust is essential in shaping human interactions with one another and with robots. In this article we investigate how human trust in robot capabilities transfers across multiple tasks. We present a...
TL;DR: This article mathematically formalizes interactions of a soft growing robot with a planar environment in an empirical kinematic model and develops a method to plan paths for the robot to a destination that is more robust to uncertainty.
Abstract: Navigation and motion control of a robot to a destination are tasks that have historically been performed with the assumption that contact with the environment is harmful. This makes sense for rigi...
TL;DR: A detailed mathematical modeling and performance analysis of parallel grippers equipped with soft fingers taking advantage of the fin ray effect (FRE) is presented, providing an analytic tool to better understand and ultimately design this type of soft fingers.
Abstract: Soft grasping of random objects in unstructured environments has been a research topic of predilection both in academia and in industry because of its complexity but great practical relevance. Howe...