Multi-Agent Pathfinding with Continuous Time

Andreychuk, Anton; Yakovlev, Konstantin; Atzmon, Dor; Stern, Roni

doi:10.24963/ijcai.2019/6

Cited by 45 publications

(19 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…under different agent number (2,3,4,8) and ρ = 2, 3, 4, 5. We can see that the maximum ASR reaches 95% when the agent number is 6 and 8, in which the minimal average baffle length is 2.95 in D 5×5 .…”

Section: Asr and Average Length Of Optimal Bafflementioning

confidence: 99%

“…It is increasingly becoming a vital component in many real‐world applications, such as famous Kiva (Amazon Robotics) warehouse systems, 1 and some autonomous aircraft towing vehicles 2 . In the pathfinding research family, multiagent pathfinding 3 and any‐angle pathfinding 4 are attracting considerable research interests from artificial intelligence (AI), robotics, theoretical computer science, and operations research. Recently, pathfinding is moving into a new direction of unknown environment‐oriented pathfinding, with the push of reinforcement learning (RL), that learns an optimal policy for agents through exhausting trials of action exploration in the unknown environment to maximize cumulative rewards.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adversarial retraining attack of asynchronous advantage actor‐critic based pathfinding

et al. 2021

View full text Add to dashboard Cite

Pathfinding becomes an important component in many real‐world scenarios, such as popular warehouse systems and autonomous aircraft towing vehicles. With the development of reinforcement learning (RL) especially in the context of asynchronous advantage actor‐critic (A3C), pathfinding is undergoing a revolution in terms of efficient parallel learning. Similar to other artificial intelligence‐based applications, A3C‐based pathfinding is also threatened by the adversarial attack. In this paper, we are the first to study the adversarial attack to A3C, that can unexpectedly wake up longtime retraining mechanism until successful pathfinding. We also discover an attack example generation to launch the attack based on gradient band, in which only one baffle of extremely few unit lengths can successfully perform the attack. Experiments with detailed analysis are conducted to show a high attack success rate of 95% with an average baffle length of 2.95. We also discuss defense suggestions leveraging the insights from our analysis.

show abstract

Section: Asr and Average Length Of Optimal Bafflementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adversarial retraining attack of asynchronous advantage actor‐critic based pathfinding

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Alternative method utilizes conflict based search (CBS) [22] to find the solution. Such as the ByPass-CBS and Continuous-Time-CBS proposed in recent work [23] and [24], which push the performance of CBS further.…”

Section: Related Workmentioning

confidence: 99%

Cooperative Pathfinding Based on Memory-Efficient Multi-Agent RRT*

Jiang

2020

IEEE Access

View full text Add to dashboard Cite

In cooperative pathfinding problems, non-conflict paths that bring several agents from their start location to their destination need to be planned. This problem can be efficiently solved by Multiagent RRT*(MA-RRT*) algorithm, which is still state-of-the-art in the field of coupled methods. However, the implementation of this algorithm is hindered in systems with limited memory because the number of nodes in the tree of RRT* grows indefinitely as the paths get optimized. This paper proposes an improved version of MA-RRT*, called Multi-agent RRT* Fixed Node(MA-RRT*FN), which limits the number of nodes stored in the tree of RRT* by removing the weak nodes on the path which are not likely to reach the goal. The results show that MA-RRT*FN performs close to MA-RRT* in terms of scalability and solution quality while the memory required is much lower and fixed.

show abstract

“…Finding a solution is one aspect of MAPF and the optimality of the solution is another aspect. According to Andreychuk et al [2], finding a valid solution is feasible in a realistic setting (i.e., it has a so-called polynomial time complexity), but finding the optimal solution may not be feasible within an acceptable timeframe (i.e., the problem has the socalled 'nP-hard' complexity: it is widely assumed that the optimal solution cannot be found in polynomial time, but no proof for this currently exists).…”

Section: Agentmentioning

confidence: 99%

Aiding vehicle Scheduling and rescheduling using Machine Learning

Wälter¹,

Mehta²,

Rao³

2020

Int. J. TDI

View full text Add to dashboard Cite

vehicle scheduling and rescheduling are central challenges for the planning and operation of railways. even though these problems have been the subject of many research and development over several decades, railways still -with good reason -at the end of the day rely on well-trained and experienced personnel to provide practical solutions to these problems. over the last couple of years, novel techniques based on machine learning have been used to propose solutions to problems such as image and speech recognition that could not have been imagined previously. the aim of machine learning is to design algorithms that can improve automatically through experience. the experience possessed by traffic dispatchers is often their greatest tool. it is, therefore, not implausible that machine learning techniques could also be used to provide better automation or support to the railway scheduling and rescheduling problems. this article describes the results of a study conducted to evaluate the extent to which solutions to the scheduling and rescheduling problems could be improved using a machine learning technique called reinforcement learning. the solutions obtained using this technique are compared with solutions obtained using classical algorithmic and constraint-based search techniques. the initial results have been obtained under a simulated environment developed by Swiss Federal railways for the public Flatland challenge competition. this research has been ranked number 4 in this international competition. Although these initial results have been obtained under simulated conditions and using limited computational resources, they look promising compared to classical scheduling and rescheduling solutions and suggest that further work in this direction could be worthwhile

show abstract

Multi-Agent Pathfinding with Continuous Time

Cited by 45 publications

References 1 publication

Adversarial retraining attack of asynchronous advantage actor‐critic based pathfinding

Adversarial retraining attack of asynchronous advantage actor‐critic based pathfinding

Cooperative Pathfinding Based on Memory-Efficient Multi-Agent RRT*

Aiding vehicle Scheduling and rescheduling using Machine Learning

Contact Info

Product

Resources

About