A Combination of Theta*, ORCA and Push and Rotate for Multi-agent Navigation

Dergachev, Stepan; Yakovlev, Konstantin; Prakapovich, Ryhor

doi:10.1007/978-3-030-60337-3_6

Cited by 7 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the most cited decentralized algorithms ORCA [27] modifies agents velocities on the fly to prevent collisions. Combinations of ORCA with centralized planning algorithms are also known [28].…”

Section: Related Workmentioning

confidence: 99%

Hybrid Policy Learning for Multi-Agent Pathfinding

et al. 2021

Self Cite

View full text Add to dashboard Cite

In this work we study the behavior of groups of autonomous vehicles, which are the part of the Internet of Vehicles systems. One of the challenging modes of operation of such systems is the case when the observability of each vehicle is limited and the global/local communication is unstable, e.g. in the crowded parking lots. In such scenarios the vehicles have to rely on the local observations and exhibit cooperative behavior to ensure safe and efficient trips. This type of problems can be abstracted to the socalled multi-agent pathfinding when a group of agents, confined to a graph, have to find collision-free paths to their goals (ideally, minimizing an objective function e.g. travel time). Widely used algorithms for solving this problem rely on the assumption that a central controller exists for which the full state of the environment (i.e. the agents current positions, their targets, configuration of the static obstacles etc.) is known and they can not be straightforwardly be adapted to the partially-observable setups. To this end, we suggest a novel approach which is based on the decomposition of the problem into the two sub-tasks: reaching the goal and avoiding the collisions. To accomplish each of this task we utilize reinforcement learning methods such as Deep Monte Carlo Tree Search, Q-mixing networks, and policy gradients methods to design the policies that map the agents' observations to actions. Next, we introduce the policy-mixing mechanism to end up with a single hybrid policy that allows each agent to exhibit both types of behavior -the individual one (reaching the goal) and the cooperative one (avoiding the collisions with other agents). We conduct an extensive empirical evaluation that shows that the suggested hybrid-policy outperforms standalone stat-ofthe-art reinforcement learning methods for this kind of problems by a notable margin.

show abstract

Section: Related Workmentioning

confidence: 99%

Hybrid Policy Learning for Multi-Agent Pathfinding

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The second challenge is about the occurrence of deadlock and oscillation in a multi-robot system, where two or more robots are stuck together and unable to resolve the situation for a long time period. While a centralized decisionmaking mechanism (see for example [11], [12] and [13]) may eventually solve the problem, it is too time-consuming and unstable to be applied to situations with only a moderate number of robots; Moreover, the evaluation and simulation of such mechanism in a discrete time-space is questionable. Some decentralized efforts can be found as well, such as [14] and [15].…”

Section: Related Workmentioning

confidence: 99%

Reciprocal Collision Avoidance for Nonholonomic Mobile Robots

Wang

Chen

et al. 2018

2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)

View full text Add to dashboard Cite

We present a method for deadlock-free and collisionfree navigation in a multi-robot system with nonholonomic robots. The problem is solved by quadratic programming and is applicable to most wheeled mobile robots with linear kinematic constraints. We introduce masked velocity and Masked Cooperative Collision Avoidance (MCCA) algorithm to encourage a fully decentralized deadlock avoidance behavior. To verify the method, we provide a detailed implementation and introduce heading oscillation avoidance for differential-drive robots. To the best of our knowledge, it is the first method to give very promising and stable results for deadlock avoidance even in situations with a large number of robots and narrow passages.

show abstract

“…This work is based on the preliminary study presented in [4]. The main novel contributions are as follows.…”

Section: Introductionmentioning

confidence: 99%

Distributed Multi-agent Navigation Based on Reciprocal Collision Avoidance and Locally Confined Multi-agent Path Finding

Dergachev¹,

Yakovlev²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Avoiding collisions is the core problem in multiagent navigation. In decentralized settings, when agents have limited communication and sensory capabilities, collisions are typically avoided in a reactive fashion, relying on local observations/communications. Prominent collision avoidance techniques, e.g. ORCA, are computationally efficient and scale well to a large number of agents. However, in numerous scenarios, involving navigation through the tight passages or confined spaces, deadlocks are likely to occur due to the egoistic behaviour of the agents and as a result, the latter can not achieve their goals. To this end, we suggest an application of the locally confined multi-agent path finding (MAPF) solvers that coordinate sub-groups of the agents that appear to be in a deadlock (to detect the latter we suggest a simple, yet efficient ad-hoc routine). We present a way to build a gridbased MAPF instance, typically required by modern MAPF solvers. We evaluate two of them in our experiments, i.e. PUSH AND ROTATE and a bounded-suboptimal version of CONFLICT BASED SEARCH (ECBS), and show that their inclusion into the navigation pipeline significantly increases the success rate, from 15% to 99% in certain cases..

show abstract

A Combination of Theta*, ORCA and Push and Rotate for Multi-agent Navigation

Cited by 7 publications

References 21 publications

Hybrid Policy Learning for Multi-Agent Pathfinding

Hybrid Policy Learning for Multi-Agent Pathfinding

Reciprocal Collision Avoidance for Nonholonomic Mobile Robots

Distributed Multi-agent Navigation Based on Reciprocal Collision Avoidance and Locally Confined Multi-agent Path Finding

Contact Info

Product

Resources

About