Cooperative, Dynamics-based, and Abstraction-Guided Multi-robot Motion Planning

Le, Duong; Plaku, Erion

doi:10.1613/jair.1.11244

Cited by 12 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the continuous setting, sampling-based motion planners are often used (Le and Plaku 2018;Hönig et al 2018). They first generate a probabilistic roadmap and then apply MAPF algorithms to it.…”

Section: Related Workmentioning

confidence: 99%

“…They first generate a probabilistic roadmap and then apply MAPF algorithms to it. These MAPF solutions are either used to guide the motion tree expansion (Le and Plaku 2018) or post-process to valid continuous trajectories (Hönig et al 2018). Similar to our approach, these algorithms can handle high-order, nonlinear dynamics, and arbitrary complex geometries.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Scalable and Safe Multi-Agent Motion Planning with Nonlinear Dynamics and Bounded Disturbances

Chen

Fan

et al. 2021

AAAI

View full text Add to dashboard Cite

We present a scalable and effective multi-agent safe motion planner that enables a group of agents to move to their desired locations while avoiding collisions with obstacles and other agents, with the presence of rich obstacles, high-dimensional, nonlinear, nonholonomic dynamics, actuation limits, and disturbances. We address this problem by finding a piecewise linear path for each agent such that the actual trajectories following these paths are guaranteed to satisfy the reach-and-avoid requirement. We show that the spatial tracking error of the actual trajectories of the controlled agents can be pre-computed for any qualified path that considers the minimum duration of each path segment due to actuation limits. Using these bounds, we find a collision-free path for each agent by solving Mixed Integer-Linear Programs and coordinate agents by using the priority-based search. We demonstrate our method by benchmarking in 2D and 3D scenarios with ground vehicles and quadrotors, respectively, and show improvements over the solving time and the solution quality compared to two state-of-the-art multi-agent motion planners.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Scalable and Safe Multi-Agent Motion Planning with Nonlinear Dynamics and Bounded Disturbances

Chen

Fan

et al. 2021

AAAI

View full text Add to dashboard Cite

show abstract

“…Finally, abstractions have also been investigated as the basis for robotic decision making (Konidaris, Kaelbling, & Lozano-Pérez, 2018) and multi-robot decision making (Le & Plaku, 2018;Amato et al, 2019). These methods typically combine temporal and state abstraction.…”

Section: Other Forms Of Abstractionmentioning

confidence: 99%

“…Thus, again, our work here is complementary, since it shows what parts of history may need to be retained to decrease this stochasticity. Le and Plaku (2018) focus on multi-robot motion planning. The difficulty here is to reason both about detailed motions, as well as the presence of multiple robots.…”

Section: Other Forms Of Abstractionmentioning

confidence: 99%

A Sufficient Statistic for Influence in Structured Multiagent Environments

Oliehoek

Witwicki

Kaelbling

2021

jair

View full text Add to dashboard Cite

Making decisions in complex environments is a key challenge in artificial intelligence (AI). Situations involving multiple decision makers are particularly complex, leading to computational intractability of principled solution methods. A body of work in AI has tried to mitigate this problem by trying to distill interaction to its essence: how does the policy of one agent influence another agent? If we can find more compact representations of such influence, this can help us deal with the complexity, for instance by searching the space of influences rather than the space of policies. However, so far these notions of influence have been restricted in their applicability to special cases of interaction. In this paper we formalize influence-based abstraction (IBA), which facilitates the elimination of latent state factors without any loss in value, for a very general class of problems described as factored partially observable stochastic games (fPOSGs). On the one hand, this generalizes existing descriptions of influence, and thus can serve as the foundation for improvements in scalability and other insights in decision making in complex multiagent settings. On the other hand, since the presence of other agents can be seen as a generalization of single agent settings, our formulation of IBA also provides a sufficient statistic for decision making under abstraction for a single agent. We also give a detailed discussion of the relations to such previous works, identifying new insights and interpretations of these approaches. In these ways, this paper deepens our understanding of abstraction in a wide range of sequential decision making settings, providing the basis for new approaches and algorithms for a large class of problems.

show abstract

“…However, many real-world problems require multiple agents to interact and cooperate. Cooperative multi-agent systems can naturally model many complex problems, including the coordination of autonomous vehicles [5], network packet delivery [44], distributed logistics [45], the control of multiple robots [20] [25], and multiplayer games [16]. Therefore, multi-agent reinforcement learning algorithms have been actively studied to enable agents to collaborate and achieve common goals [4].…”

Section: Introductionmentioning

confidence: 99%

Cooperative Multi-Agent Reinforcement Learning With Approximate Model Learning

2020

View full text Add to dashboard Cite

In multi-agent reinforcement learning, it is essential for agents to learn communication protocol to optimize collaboration policies and to solve unstable learning problems. Existing methods based on actorcritic networks solve the communication problem among agents. However, these methods have difficulty in improving sample efficiency and learning robust policies because it is not easy to understand the dynamics and nonstationary of the environment as the policies of other agents change. We propose a method for learning cooperative policies in multi-agent environments by considering the communications among agents. The proposed method consists of recurrent neural network-based actor-critic networks and deterministic policy gradients to centrally train decentralized policies. The actor networks cause the agents to communicate using forward and backward paths and to determine subsequent actions. The critic network helps to train the actor networks by sending gradient signals to the actors according to their contribution to the global reward. To address issues with partial observability and unstable learning, we propose using auxiliary prediction networks to approximate state transitions and the reward function. We used multi-agent environments to demonstrate the usefulness and superiority of the proposed method by comparing it with existing multi-agent reinforcement learning methods, in terms of both learning efficiency and goal achievements in the test phase. The results demonstrate that the proposed method outperformed other alternatives. INDEX TERMS reinforcement learning, model-free method, multi-agent system, multi-agent cooperation, actor-critic method, deterministic policy gradient SECTION I.

show abstract

Cooperative, Dynamics-based, and Abstraction-Guided Multi-robot Motion Planning

Cited by 12 publications

References 37 publications

Scalable and Safe Multi-Agent Motion Planning with Nonlinear Dynamics and Bounded Disturbances

Scalable and Safe Multi-Agent Motion Planning with Nonlinear Dynamics and Bounded Disturbances

A Sufficient Statistic for Influence in Structured Multiagent Environments

Cooperative Multi-Agent Reinforcement Learning With Approximate Model Learning

Contact Info

Product

Resources

About