Links: [PDF]

Abstract: We study the problem of deploying a fleet of mobile robots to service tasks that arrive stochastically over time and at random locations in an environment. This is known as the Dynamic Vehicle Routing Problem (DVRP) and requires robots to allocate incoming tasks among themselves and find an optimal sequence for each robot. State-of-the-art approaches only consider average wait times and focus on high-load scenarios where the arrival rate of tasks approaches the limit of what can be handled by the robots while keeping the queue of unserviced tasks bounded, i.e., stable. To ensure stability, these approaches repeatedly compute minimum distance tours over a set of newly arrived tasks. This letter is aimed at addressing the missing policies for moderate-load scenarios, where quality of service can be improved by prioritizing long-waiting tasks. We introduce a novel DVRP policy based on a cost function that takes the p-norm over accumulated wait times and show it guarantees stability even in high-load scenarios. We demonstrate that the proposed policy outperforms the state-of-the-art in both mean and 95th percentile wait times in moderate-load scenarios through simulation experiments in the Euclidean plane as well as using real-world data for city scale service requests.

Links: [web], [PDF],

Abstract: This paper studies the multi-robot task assignment problem in which a fleet of dispersed robots needs to efficiently transport a set of dynamically appearing packages from their initial locations to corresponding destinations within prescribed time-windows. Each robot can carry multiple packages simultaneously within its capacity. Given a sufficiently large robot fleet, the objective is to minimize the robots’ total travel time to transport the packages within their respective time-window constraints. The problem is shown to be NP-hard, and we design two group-based distributed auction algorithms to solve this task assignment problem. Guided by the auction algorithms, robots first distributively calculate feasible package groups that they can serve, and then communicate to find an assignment of package groups. We quantify the potential of the algorithms with respect to the number of employed robots and the capacity of the robots by considering the robots’ total travel time to transport all packages. Simulation results show that the designed algorithms are competitive compared with an exact centralized Integer Linear Program representation solved with the commercial solver Gurobi, and superior to popular greedy algorithms and a heuristic distributed task allocation method.

Links: [web], [PDF], [code], [video]

Abstract: Autonomous mobile robots require accurate human motion predictions to safely and efficiently navigate among pedestrians, whose behavior may adapt to environmental changes. This paper introduces a self-supervised continual learning framework to improve data-driven pedestrian prediction models online across various scenarios continuously. In particular, we exploit online streams of pedestrian data, commonly available from the robot’s detection and tracking pipeline, to refine the prediction model and its performance in unseen scenarios. To avoid the forgetting of previously learned concepts, a problem known as catastrophic forgetting, our framework includes a regularization loss to penalize changes of model parameters that are important for previous scenarios and retrains on a set of previous examples to retain past knowledge. Experimental results on real and simulation data show that our approach can improve prediction performance in unseen scenarios while retaining knowledge from seen scenarios when compared to naively training the prediction model online.

Links: [web], [PDF], [code], [video]

Abstract: Robotic navigation in environments shared with other robots or humans remains challenging because the intentions of the surrounding agents are not directly observable and the environment conditions are continuously changing. Local trajectory optimization methods, such as model predictive control (MPC), can deal with those changes but require global guidance, which is not trivial to obtain in crowded scenarios. This paper proposes to learn, via deep Reinforcement Learning (RL), an interaction-aware policy that provides long-term guidance to the local planner. In particular, in simulations with cooperative and non-cooperative agents, we train a deep network to recommend a subgoal for the MPC planner. The recommended subgoal is expected to help the robot in making progress towards its goal and accounts for the expected interaction with other agents. Based on the recommended subgoal, the MPC planner then optimizes the inputs for the robot satisfying its kinodynamic and collision avoidance constraints. Our approach is shown to substantially improve the navigation performance in terms of number of collisions as compared to prior MPC frameworks, and in terms of both travel time and number of collisions compared to deep RL methods in cooperative, competitive and mixed multiagent scenarios.

Links: [PDF], [code], [video]

Abstract: In this paper, we address the problem of real-time motion planning for multiple robotic manipulators that operate in close proximity. We build upon the concept of dynamic fabrics and extend them to multi-robot systems, referred to as Multi-Robot Dynamic Fabrics (MRDF). This geometric method enables a very high planning frequency for high-dimensional systems at the expense of being reactive and prone to deadlocks. To detect and resolve deadlocks, we propose Rollout Fabrics where MRDF are forward simulated in a decentralized manner. We validate the methods in simulated close-proximity pick-and-place scenarios with multiple manipulators, showing high success rates and real-time performance.

Links: [PDF],

Abstract: Reward learning is a highly active area of research in human-robot interaction (HRI), allowing a broad range of users to specify complex robot be- haviour. Experiments with simulated user input play a major role in the devel- opment and evaluation of reward learning algorithms due to the availability of a ground truth. In this paper, we review measures for evaluating reward learning algorithms used in HRI, most of which fall into two classes. In a theoretical worst case analysis and several examples, we show that both classes of measures can fail to effectively indicate how good the learned robot behaviour is. Thus, our work contributes to the characterization of sim-to-real gaps of reward learning in HRI.

Links: [PDF],

Abstract: In this paper we study the multi-robot task assignment problem with tasks that appear online and need to be serviced within a fixed time window in an uncertain environment. For example, when deployed in dynamic, humancentered environments, the team of robots may not have perfect information about the environment. Parts of the environment may temporarily become blocked and blockages may only be observed on location. While numerous variants of the Canadian Traveler Problem describe the path planning aspect of this problem, few work has been done on multi-robot task allocation (MRTA) under this type of uncertainty. In this paper, we introduce and theoretically analyze the problem of MRTA with recoverable online blockages. Based on a stochastic blockage model, we compute offline tours using the expected travel costs for the online routing problem. The cost of the offline tours is used in a greedy task assignment algorithm. In simulation experiments we highlight the performance benefits of the proposed method under various settings.

Links: [web], [PDF],

Abstract: Many problems in robotics seek to simultaneously optimize several competing objectives under constraints. A conventional approach to solving such multi-objective optimization problems is to create a single cost function comprised of the weighted sum of the individual objectives. Solutions to this scalarized optimization problem are Pareto optimal solutions to the original multi-objective problem. However, finding an accurate representation of a Pareto front remains an important challenge. Using uniformly spaced weight vectors is often inefficient and does not provide error bounds. Thus, we address the problem of computing a finite set of weight vectors such that for any other weight vector, there exists an element in the set whose error compared to optimal is minimized. To this end, we prove fundamental properties of the optimal cost as a function of the weight vector, including its continuity and concavity. Using these, we propose an algorithm that greedily adds the weight vector least-represented by the current set, and provide bounds on the error. Finally, we illustrate that the proposed approach significantly outperforms uniformly distributed weights for different robot planning problems with varying numbers of objective functions.