Real time cooperative path planning for multi-autonomous vehicles

Francis, Sobers L X; Anavatti, Sreenatha G.; Garratt, Matthew A.

doi:10.1109/icacci.2013.6637322

Cited by 10 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, the results in [4] allow UAVs or AGVs to share the sensor data among vehicles. But transmitting all the depth averaged flow data within a glider patch over underwater communication link or satellite communication link, the two major communication methods used by gliders, is difficult and even unachievable.…”

Section: Problem Formulationmentioning

confidence: 98%

“…Existing work on cooperative path planning mainly focus on Autonomous Ground Vehicles (AGVs) and Unmanned Aerial Vehicles (UAVs). Results in [4] requires that each vehicle in the group to share their kinematic and sensor information with others. Each vehicle can re-plan its path based on its own sensor data and sensor data received from other vehicles.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cooperative Path Planning for Networked Gliders under Weak Communication

Liu¹,

Yu²,

Zhang³

et al. 2014

Proceedings of the International Conference on Underwater Networks %Systems - WUWNET '14

View full text Add to dashboard Cite

This paper presents a distributed approach for cooperative path planning for underwater gliders to avoid regions with strong ocean flow. A key requirement for underwater glider operation is to reduce the amount of information that needs to be shared among gliders over communication links. For this purpose, the proposed approach employs the support vector data description method to form a compressed representation of the high flow region that gliders should avoid. A fast marching algorithm is then developed to use the compressed information shared by gliders. Simulation results show that the quality of the planned path based on the compressed information is comparable to the case when full information of flow would have been shared.

show abstract

Section: Problem Formulationmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Cooperative Path Planning for Networked Gliders under Weak Communication

Liu¹,

Yu²,

Zhang³

et al. 2014

Proceedings of the International Conference on Underwater Networks %Systems - WUWNET '14

View full text Add to dashboard Cite

show abstract

“…where x s , x k ∈ S. The number of support vectors can be adjusted by two parameters: the weight C in (7) and the width σ in the Gaussian kernel K G . Parameter C is not critical in practice [22], hence we will determine σ.…”

Section: Appendix Review Of Support Vector Data Descriptionmentioning

confidence: 99%

“…So far, existing works on cooperative or distributed path planning mainly focus on autonomous ground vehicles and unmanned aerial vehicles (UAVs). For instance, results in [7] require that each vehicle in the group has to share the kinematic and sensor information with others so that each vehicle can replan its path based on its own sensor data and those received from other vehicles. In [8], paths that avoid no-fly zones and obstacles for multiple UAVs are generated.…”

mentioning

confidence: 99%

Distributed Traversability Analysis of Flow Field Under Communication Constraints

Liu

Sun

et al. 2019

IEEE J. Oceanic Eng.

View full text Add to dashboard Cite

Traversability analysis, previously developed for ground robots, is extended to be performed by a group of marine vehicles over ocean flow fields. To enable distributed path planning against flow, a systematic method is developed to determine a flow map that is significant for sharing among vehicles. Using traversability analysis, each vehicle finds a set of support vectors to approximate the boundary of flow regions with strong average flow speed. These support vectors, together with the parameters determined by the traversability analysis, are then shared over the communication links. The shared information is used by each vehicle to construct a flow map that supports path planning algorithms running on each vehicle. Underwater communication limits the amount of information contained in a map that can be shared among vehicles. A novel method for information reduction is developed so that only reduced flow maps are shared. The length of the data packets can be adjusted through an optimization process that balance between the fidelity of the approximated boundary and the number of bits that need to be transmitted. Simulation results demonstrate that the flow maps constructed from the shared information can have sufficient quality to allow near-optimal paths to be generated.

show abstract

“…Planning a safe and efficient path for each UV is still one of the challenges for mission planning. Obstacle avoidance, as well as collision avoidance among agents, plays an important role in the context of managing multiple agents [6]. On the way to the selected locations, all UVs should be able to avoid obstacles by replanning their path dynamically.…”

Section: Introductionmentioning

confidence: 99%

A Time-Efficient Co-Operative Path Planning Model Combined with Task Assignment for Multi-Agent Systems

2019

Self Cite

View full text Add to dashboard Cite

Dealing with uncertainties along with high-efficiency planning for task assignment problem is still challenging, especially for multi-agent systems. In this paper, two frameworks—Compromise View model and the Nearest-Neighbour Search model—are analyzed and compared for co-operative path planning combined with task assignment of a multi-agent system in dynamic environments. Both frameworks are capable of dynamically controlling a number of autonomous agents to accomplish multiple tasks at different locations. Furthermore, these two models are capable of dealing with dynamically changing environments. In both approaches, the Particle Swarm Optimization-based method is applied for path planning. The path planning approach combined with the obstacle avoidance strategy is integrated with the task assignment problem. In one framework, the Compromise View model is used for completing the tasks and a combination of clustering method with the Nearest-Neighbour Search model is used to assign tasks to the other framework. The frameworks are compared in terms of computational time and the resulting path length. Results indicate that the Nearest-Neighbour Search model is much faster than the Compromise View model. However, the Nearest-Neighbour Search model generates longer paths to accomplish the mission. By following the Nearest-Neighbour Search approach, agents can successfully accomplish their mission, even under uncertainties such as malfunction of individual agents. The Nearest-Neighbour Search framework is highly effective due to its reactive structure. As per requirements, to save time, after completing its own tasks, one agent can complete the remaining tasks of other agents. The simulation results show that the Nearest-Neighbour Search model is an effective and robust way of solving co-operative path planning combined with task assignment problems.

show abstract

Real time cooperative path planning for multi-autonomous vehicles

Cited by 10 publications

References 0 publications

Cooperative Path Planning for Networked Gliders under Weak Communication

Cooperative Path Planning for Networked Gliders under Weak Communication

Distributed Traversability Analysis of Flow Field Under Communication Constraints

A Time-Efficient Co-Operative Path Planning Model Combined with Task Assignment for Multi-Agent Systems

Contact Info

Product

Resources

About