Robert Pěnička

Bio: Robert Pěnička is an academic researcher from Czech Technical University in Prague. The author has contributed to research in topics: Orienteering & Motion planning. The author has an hindex of 4, co-authored 8 publications receiving 109 citations.

Unsupervised learning‐based flexible framework for surveillance planning with aerial vehicles

Abstract: The herein studied problem is motivated by practical needs of our participation in the Mohamed Bin Zayed International Robotics Challenge (MBZIRC) 2017 in which a team of Unmanned Aerial Vehicles (UAVs) is requested to collect objects in the given area as quickly as possible and score according to the rewards associated with the objects. The mission time is limited, and the most time-consuming operation is the collection of the objects themselves. Therefore, we address the problem to quickly identify the most valuable objects as surveillance planning with curvature-constrained trajectories. The problem is formulated as a multi-vehicle variant of the Dubins Traveling Salesman Problem with Neighborhoods (DTSPN). Based on the evaluation of existing approaches to the DTSPN, we propose to use unsupervised learning to find satisfiable solutions with low computational requirements. Moreover, the flexibility of unsupervised learning allows considering trajectory parametrization that better fits the motion constraints of the utilized hexacopters that are not limited by the minimal turning radius as the Dubins vehicle. We propose to use Bézier curves to exploit the maximal vehicle velocity and acceleration limits. Besides, we further generalize the proposed approach to 3D surveillance planning. We report on evaluation results of the developed algorithms and experimental verification of the planned trajectories using the real UAVs utilized in our participation in MBZIRC 2017.

Data collection planning with non-zero sensing distance for a budget and curvature constrained unmanned aerial vehicle

Abstract: Data collection missions are one of the many effective use cases of unmanned aerial vehicles (UAVs), where the UAV is required to visit a predefined set of target locations to retrieve data. However, the flight time of a real UAV is time constrained, and therefore only a limited number of target locations can typically be visited within the mission. In this paper, we address the data collection planning problem called the Dubins Orienteering Problem with Neighborhoods (DOPN), which sets out to determine the sequence of visits to the most rewarding subset of target locations, each with an associated reward, within a given travel budget. The objective of the DOPN is thus to maximize the sum of the rewards collected from the visited target locations using a budget constrained path between predefined starting and ending locations. The variant of the orienteering problem addressed here uses curvature-constrained Dubins vehicle model for planning the data collection missions for UAV. Moreover, in the DOPN, it is also assumed that the data, and thus the reward, may be collected from a close neighborhood sensing distance around the target locations, e.g., taking a snapshot by an onboard camera with a wide field of view, or using a sensor with a long range. We propose a novel approach based on the Variable Neighborhood Search (VNS) metaheuristic for the DOPN, in which combinatorial optimization of the sequence for visiting the target locations is simultaneously addressed with continuous optimization for finding Dubins vehicle waypoints inside the neighborhoods of the visited targets. The proposed VNS-based DOPN algorithm is evaluated in numerous benchmark instances, and the results show that it significantly outperforms the existing methods in both solution quality and computational time. The practical deployability of the proposed approach is experimentally verified in a data collection scenario with a real hexarotor UAV.

Multi-goal path planning using multiple random trees

Abstract: In this paper, we propose a novel sampling-based planner for multi-goal path planning among obstacles, where the objective is to visit predefined target locations while minimizing the travel costs. The order of visiting the targets is often achieved by solving the Traveling Salesman Problem (TSP) or its variants. TSP requires to define costs between the individual targets, which - in a map with obstacles - requires to compute mutual paths between the targets. These paths, found by path planning, are used both to define the costs (e.g., based on their length or time-to-traverse) and also they define paths that are later used in the final solution. To enable TSP finding a good-quality solution, it is necessary to find these target-to-target paths as short as possible. We propose a sampling-based planner called Space-Filling Forest (SFF*) that solves the part of finding collision-free paths. SFF* uses multiple trees (forest) constructed gradually and simultaneously from the targets and attempts to find connections with other trees to form the paths. Unlike Rapidly-exploring Random Tree (RRT), which uses the nearest-neighbor rule for selecting nodes for expansion, SFF* maintains an explicit list of nodes for expansion. Individual trees are grown in a RRT* manner, i.e., with rewiring the nodes to minimize their cost. Computational results show that SFF* provides shorter target-to-target paths than existing approaches, and consequently, the final TSP solutions also have a lower cost.

Model Predictive Trajectory Tracking and Collision Avoidance for Reliable Outdoor Deployment of Unmanned Aerial Vehicles

Abstract: We propose a novel approach for optimal trajectory tracking for unmanned aerial vehicles (UAV), using a linear model predictive controller (MPC) in combination with non-linear state feedback. The solution relies on fast onboard simulation of the translational dynamics of the UAV, which is guided by a linear MPC. By sampling the states of the virtual UAV, we create a control command for fast non-linear feedback, which is capable of performing agile maneuvers with high precision. In addition, the proposed pipeline provides an interface for a decentralized collision avoidance system for multi-UAY scenarios. Our solution makes use of the long prediction horizon of the linear MPC and allows safe outdoors execution of multi-UAV experiments without the need for in-advance collision-free planning. The practicality of the tracking mechanism is shown in combination with priority-based collision resolution strategy, which performs sufficiently in experiments with up to 5 UAVs. We present a statistical and experimental evaluation of the platform in both simulation and real-world examples, demonstrating the usability of the approach.

Autonomous landing on a moving vehicle with an unmanned aerial vehicle

Abstract: This paper addresses the perception, control and trajectory planning for an aerial platform to identify and land on a moving car at 15 km/h. The hexacopter Unmanned Aerial Vehicle (UAV), equipped with onboard sensors and a computer, detects the car using a monocular camera and predicts the car future movement using a nonlinear motion model. While following the car, the UAV lands on its roof, and it attaches itself using magnetic legs. The proposed system is fully autonomous from takeoff to landing. Numerous field tests were conducted throughout the year-long development and preparations for the MBZIRC 2017 competition, for which the system was designed. We propose a novel control system in which a Model Predictive Controller is used in real time to generate a reference trajectory for the UAV, which are then tracked by the nonlinear feedback controller. This combination allows to track predictions of the car motion with minimal position error. The evaluation presents three successful autonomous landings during the MBZIRC 2017, where our system achieved the fastest landing among all competing teams. ∗http://mrs.felk.cvut.cz †http://www.grasp.upenn.edu

DARPA Subterranean Challenge: Multi-robotic Exploration of Underground Environments

Abstract: The Subterranean Challenge (SubT) is a contest organised by the Defense Advanced Research Projects Agency (DARPA). The contest reflects the requirement of increasing safety and efficiency of underground search-and-rescue missions. In the SubT challenge, teams of mobile robots have to detect, localise and report positions of specific objects in an underground environment. This paper provides a description of the multi-robot heterogeneous exploration system of our CTU-CRAS team, which scored third place in the Tunnel Circuit round, surpassing the performance of all other non-DARPA-funded competitors. In addition to the description of the platforms, algorithms and strategies used, we also discuss the lessons-learned by participating at such contest.

A Survey on Swarming With Micro Air Vehicles: Fundamental Challenges and Constraints

Abstract: This work presents a review and discussion of the challenges that must be solved in order to successfully develop swarms of Micro Air Vehicles (MAVs) for real world operations. From the discussion, we extract constraints and links that relate the local level MAV capabilities to the global operations of the swarm. These should be taken into account when designing swarm behaviors in order to maximize the utility of the group. At the lowest level, each MAV should operate safely. Robustness is often hailed as a pillar of swarm robotics, and a minimum level of local reliability is needed for it to propagate to the global level. An MAV must be capable of autonomous navigation within an environment with sufficient trustworthiness before the system can be scaled up. Once the operations of the single MAV are sufficiently secured for a task, the subsequent challenge is to allow the MAVs to sense one another within a neighborhood of interest. Relative localization of neighbors is a fundamental part of self-organizing robotic systems, enabling behaviors ranging from basic relative collision avoidance to higher level coordination. This ability, at times taken for granted, also must be sufficiently reliable. Moreover, herein lies a constraint: the design choice of the relative localization sensor has a direct link to the behaviors that the swarm can (and should) perform. Vision-based systems, for instance, force MAVs to fly within the field of view of their camera. Range or communication-based solutions, alternatively, provide omni-directional relative localization, yet can be victim to unobservable conditions under certain flight behaviors, such as parallel flight, and require constant relative excitation. At the swarm level, the final outcome is thus intrinsically influenced by the on-board abilities and sensors of the individual. The real-world behavior and operations of an MAV swarm intrinsically follow in a bottom-up fashion as a result of the local level limitations in cognition, relative knowledge, communication, power, and safety. Taking these local limitations into account when designing a global swarm behavior is key in order to take full advantage of the system, enabling local limitations to become true strengths of the swarm.