arXiv subjects

Amanda Prorok

Publications and source records attributed to Amanda Prorok.

85 records · Page 5Linked to original sources

arXiv2020

Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning

Path planning for mobile robots in large dynamic environments is a challenging problem, as the robots are required to efficiently reach their given goals while simultaneously avoiding potential conflicts with other robots or dynamic objects. In the presence of dynamic obstacles, traditional solutions usually employ re-planning strategies, which re-call a planning algorithm to search for an alternative path whenever the robot encounters a conflict. However, such re-planning strategies often cause unnecessary detours. To address this issue, we propose a learning-based technique that exploits environmental spatio-temporal information. Different from existing learning-based methods, we introduce a globally guided reinforcement learning approach (G2RL), which incorporates a novel reward structure that generalizes to arbitrary environments. We apply G2RL to solve the multi-robot path planning problem in a fully distributed reactive manner. We evaluate our method across different map types, obstacle densities, and the number of robots. Experimental results show that G2RL generalizes well, outperforming existing distributed methods, and performing very similarly to fully centralized state-of-the-art benchmarks.

cs.RO↗

arXiv2020

Graph Neural Networks for Decentralized Multi-Robot Path Planning

Effective communication is key to successful, decentralized, multi-robot path planning. Yet, it is far from obvious what information is crucial to the task at hand, and how and when it must be shared among robots. To side-step these issues and move beyond hand-crafted heuristics, we propose a combined model that automatically synthesizes local communication and decision-making policies for robots navigating in constrained workspaces. Our architecture is composed of a convolutional neural network (CNN) that extracts adequate features from local observations, and a graph neural network (GNN) that communicates these features among robots. We train the model to imitate an expert algorithm, and use the resulting model online in decentralized planning involving only local communication and local observations. We evaluate our method in simulations {by navigating teams of robots to their destinations in 2D} cluttered workspaces. We measure the success rates and sum of costs over the planned paths. The results show a performance close to that of our expert algorithm, demonstrating the validity of our approach. In particular, we show our model's capability to generalize to previously unseen cases (involving larger environments and larger robot teams).

cs.RO↗

arXiv2020

Effects of Controller Heterogeneity on Autonomous Vehicle Traffic

Interactions between road users are both highly non-linear and profoundly complex, and there is no reason to expect that interactions between autonomous vehicles will be any different. Given the recent rapid development of autonomous vehicle technologies, we need to understand how these interactions are likely to present themselves, and what their implications might be. This paper looks into the impact of autonomous vehicles with differing controllers, focusing specifically on the effects of changing the mean and heterogeneity of controller parameters on three key performance metrics: throughput, passenger safety and comfort. Towards this end, we develop a method for systematically sampling vehicle controllers as a function of parameter heterogeneity. In addition to evaluating the impact of heterogeneity on performance, we quantify the relative impacts of controller input parameters on the output performance metrics by means of sensitivity analyses. The MovSim traffic simulator was used to simulate a realistic traffic system, whilst recording maximum throughput, as well as lane change frequencies and mean absolute accelerations as proxies for safety and comfort. Our results reveal that traffic performance is primarily affected by the heterogeneity of vehicle target velocities, as well as by the mean values of a very small subset of the parameters, of which the target velocity is by far the most significant.

eess.SY↗

arXiv2020

Multi-Vehicle Mixed-Reality Reinforcement Learning for Autonomous Multi-Lane Driving

Autonomous driving promises to transform road transport. Multi-vehicle and multi-lane scenarios, however, present unique challenges due to constrained navigation and unpredictable vehicle interactions. Learning-based methods---such as deep reinforcement learning---are emerging as a promising approach to automatically design intelligent driving policies that can cope with these challenges. Yet, the process of safely learning multi-vehicle driving behaviours is hard: while collisions---and their near-avoidance---are essential to the learning process, directly executing immature policies on autonomous vehicles raises considerable safety concerns. In this article, we present a safe and efficient framework that enables the learning of driving policies for autonomous vehicles operating in a shared workspace, where the absence of collisions cannot be guaranteed. Key to our learning procedure is a sim2real approach that uses real-world online policy adaptation in a mixed-reality setup, where other vehicles and static obstacles exist in the virtual domain. This allows us to perform safe learning by simulating (and learning from) collisions between the learning agent(s) and other objects in virtual reality. Our results demonstrate that, after only a few runs in mixed-reality, collisions are significantly reduced.

cs.RO↗

arXiv2020

An Adversarial Approach to Private Flocking in Mobile Robot Teams

Privacy is an important facet of defence against adversaries. In this letter, we introduce the problem of private flocking. We consider a team of mobile robots flocking in the presence of an adversary, who is able to observe all robots' trajectories, and who is interested in identifying the leader. We present a method that generates private flocking controllers that hide the identity of the leader robot. Our approach towards privacy leverages a data-driven adversarial co-optimization scheme. We design a mechanism that optimizes flocking control parameters, such that leader inference is hindered. As the flocking performance improves, we successively train an adversarial discriminator that tries to infer the identity of the leader robot. To evaluate the performance of our co-optimization scheme, we investigate different classes of reference trajectories. Although it is reasonable to assume that there is an inherent trade-off between flocking performance and privacy, our results demonstrate that we are able to achieve high flocking performance and simultaneously reduce the risk of revealing the leader.

cs.RO↗

arXiv2019

Culture-Based Explainable Human-Agent Deconfliction

Law codes and regulations help organise societies for centuries, and as AI systems gain more autonomy, we question how human-agent systems can operate as peers under the same norms, especially when resources are contended. We posit that agents must be accountable and explainable by referring to which rules justify their decisions. The need for explanations is associated with user acceptance and trust. This paper's contribution is twofold: i) we propose an argumentation-based human-agent architecture to map human regulations into a culture for artificial agents with explainable behaviour. Our architecture leans on the notion of argumentative dialogues and generates explanations from the history of such dialogues; and ii) we validate our architecture with a user study in the context of human-agent path deconfliction. Our results show that explanations provide a significantly higher improvement in human performance when systems are more complex. Consequently, we argue that the criteria defining the need of explanations should also consider the complexity of a system. Qualitative findings show that when rules are more complex, explanations significantly reduce the perception of challenge for humans.

cs.MA↗

arXiv2019

Multi-Robot Path Deconfliction through Prioritization by Path Prospects

This work deals with the problem of planning conflict-free paths for mobile robots in cluttered environments. Since centralized, coupled planning algorithms are computationally intractable for large numbers of robots, we consider decoupled planning, in which robots plan their paths sequentially in order of priority. Choosing how to prioritize the robots is a key consideration. State-of-the-art prioritization heuristics, however, do not model the coupling between a robot's mobility and its environment. In this paper, we propose a prioritization rule that can be computed online by each robot independently, and that provides consistent, conflict-free path plans. Our innovation is to formalize a robot's path prospects to reach its goal from its current location. To this end, we consider the number of homology classes of trajectories, and use this as a prioritization rule in our decentralized path planning algorithm, whenever any robots enter negotiation to deconflict path plans. This prioritization rule guarantees a partial ordering over the robot set. We perform simulations that compare our method to five benchmarks, and show that it reaches the highest success rate (w.r.t. completeness), and that it strikes the best balance between makespan and flowtime objectives.

cs.RO↗

arXiv2019

Resilient Assignment Using Redundant Robots on Transport Networks with Uncertain Travel Time

This paper considers the problem of assigning multiple mobile robots to goals on transport networks with uncertain information about travel times. Our aim is to produce optimal assignments, such that the average waiting time at destinations is minimized. Since noisy travel time estimates result in sub-optimal assignments, we propose a method that offers resilience to uncertainty by making use of redundant robots. However, solving the redundant assignment problem optimally is strongly NP-hard. Hence, we exploit structural properties of our mathematical problem formulation to propose a polynomial-time, near-optimal solution. We demonstrate that our problem can be reduced to minimizing a supermodular cost function subject to a matroid constraint. This allows us to develop a greedy algorithm, for which we derive sub-optimality bounds. We demonstrate the effectiveness of our approach with simulations on transport networks, where uncertain edge costs and uncertain node positions lead to noisy travel time estimates. Comparisons to benchmark algorithms show that our method performs near-optimally and significantly better than non-redundant assignment. Finally, our findings include results on the benefit of diversity and complementarity in redundant robot coalitions; these insights contribute towards providing resilience to uncertainty through targeted robot team compositions.

cs.RO↗

arXiv2019

A Fleet of Miniature Cars for Experiments in Cooperative Driving

We introduce a unique experimental testbed that consists of a fleet of 16 miniature Ackermann-steering vehicles. We are motivated by a lack of available low-cost platforms to support research and education in multi-car navigation and trajectory planning. This article elaborates the design of our miniature robotic car, the Cambridge Minicar, as well as the fleet's control architecture. Our experimental testbed allows us to implement state-of-the-art driver models as well as autonomous control strategies, and test their validity in a real, physical multi-lane setup. Through experiments on our miniature highway, we are able to tangibly demonstrate the benefits of cooperative driving on multi-lane road topographies. Our setup paves the way for indoor large-fleet experimental research.

cs.RO↗

arXiv2019

Graph Neural Networks for Learning Robot Team Coordination

This paper shows how Graph Neural Networks can be used for learning distributed coordination mechanisms in connected teams of robots. We capture the relational aspect of robot coordination by modeling the robot team as a graph, where each robot is a node, and edges represent communication links. During training, robots learn how to pass messages and update internal states, so that a target behavior is reached. As a proxy for more complex problems, this short paper considers the problem where each robot must locally estimate the algebraic connectivity of the team's network topology.

cs.RO↗

arXiv2018

Redundant Robot Assignment on Graphs with Uncertain Edge Costs

We provide a framework for the assignment of multiple robots to goal locations, when robot travel times are uncertain. Our premise is that time is the most valuable asset in the system. Hence, we make use of redundant robots to counter the effect of uncertainty and minimize the average waiting time at destinations. We apply our framework to transport networks represented as graphs, and consider uncertainty in the edge costs (i.e., travel time). Since solving the redundant assignment problem is strongly NP-hard, we exploit structural properties of our problem to propose a polynomial-time solution with provable sub-optimality bounds. Our method uses distributive aggregate functions, which allow us to efficiently (i.e., incrementally) compute the effective cost of assigning redundant robots. Experimental results on random graphs show that the deployment of redundant robots through our method reduces waiting times at goal locations, when edge traversals are uncertain.

cs.RO↗

arXiv2017

Privacy-Preserving Vehicle Assignment for Mobility-on-Demand Systems

Urban transportation is being transformed by mobility-on-demand (MoD) systems. One of the goals of MoD systems is to provide personalized transportation services to passengers. This process is facilitated by a centralized operator that coordinates the assignment of vehicles to individual passengers, based on location data. However, current approaches assume that accurate positioning information for passengers and vehicles is readily available. This assumption raises privacy concerns. In this work, we address this issue by proposing a method that protects passengers' drop-off locations (i.e., their travel destinations). Formally, we solve a batch assignment problem that routes vehicles at obfuscated origin locations to passenger locations (since origin locations correspond to previous drop-off locations), such that the mean waiting time is minimized. Our main contributions are two-fold. First, we formalize the notion of privacy for continuous vehicle-to-passenger assignment in MoD systems, and integrate a privacy mechanism that provides formal guarantees. Second, we present a scalable algorithm that takes advantage of superfluous (idle) vehicles in the system, combining multiple iterations of the Hungarian algorithm to allocate a redundant number of vehicles to a single passenger. As a result, we are able to reduce the performance deterioration induced by the privacy mechanism. We evaluate our methods on a real, large-scale data set consisting of over 11 million taxi rides (specifying vehicle availability and passenger requests), recorded over a month's duration, in the area of Manhattan, New York. Our work demonstrates that privacy can be integrated into MoD systems without incurring a significant loss of performance, and moreover, that this loss can be further minimized at the cost of deploying additional (redundant) vehicles into the fleet.

cs.CR↗

arXiv2017

A Macroscopic Model for Differential Privacy in Dynamic Robotic Networks

The increasing availability of online and mobile information platforms is facilitating the development of peer-to-peer collaboration strategies in large-scale networks. These technologies are being leveraged by networked robotic systems to provide applications of automated transport, resource redistribution (collaborative consumption), and location services. Yet, external observations of the system dynamics may expose sensitive information about the participants that compose these networks (robots, resources, and humans). In particular, we are concerned with settings where an adversary gains access to a snapshot of the dynamic state of the system. We propose a method that quantifies how easy it is for the adversary to identify the specific type of any agent (which can be a robot, resource, or human) in the network, based on this observation. We draw from the theory of differential privacy to propose a closed-form expression for the leakage of the system when the snapshot is taken at steady-state, as well as a numerical approach to compute the leakage when the snapshot is taken at any given time. The novelty of our approach is that our privacy model builds on a macroscopic description of the system's state, which allows us to take account of protected entities (network participants) that are interdependent. Our results show how the leakage varies, as a function of the composition and dynamic behavior of the network; they also indicate design rules for increasing privacy levels.

cs.RO↗