PPCPP: A Predator–Prey-Based Approach to Adaptive Coverage Path Planning

Hassan, Mahdi; Liu, Dikai

doi:10.1109/tro.2019.2946891

Cited by 47 publications

(16 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3c and 3d (for scenario 2 with 3 robots), when R d p is set to zero, the paths are not only less efficient but also very chaotic. Note that other reward functions have already been validated in the previous work [15]. Video for the scenario shown in Fig.…”

Section: A Case Study 1: Coverage Amid Stationary Obstaclesmentioning

confidence: 72%

“…In Dec-PPCPP, each robot considers itself a prey that needs to avoid predation from two types of predators: 1) a stationary virtual predator, and 2) dynamic predators (other robots). In this subsection, the stationary predator avoidance reward is formulated, which is similar to the work in [15]. A prey, while searching the target area for food (to achieve coverage), aims to continually maximize it distance to a stationary predator, denoted as Ψ s i where i is the robot index.…”

Section: A Stationary Predator Avoidance Rewardmentioning

confidence: 99%

“…As such, the prey is given an extra reward for continuing motion in a straight direction. This reward function, which is similar to the work in [15], is formulated as follows:…”

Section: Smoothness Rewardmentioning

confidence: 99%

“…To query, delete or insert a point in the k-d tree, the time complexity is O(log m) where m is the number of targets in the set O. Therefore, following the same procedure as in the previous work [15], the time complexity for finding the neighbor with maximum reward (Alg. 2: line 7 to 14) is O(log m).…”

Section: A Computational Complexitymentioning

confidence: 99%

“…The concept of PPCPP has been investigated for single robot coverage planning problem [15]. This paper aims at addressing the decentralized multi-robot coverage planning problem by developing a decentralized PPCPP approach (Dec-PPCPP).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Dec-PPCPP: A Decentralized Predator–Prey-based Approach to Adaptive Coverage Path Planning Amid Moving Obstacles

Hassan

Mustafic

Liu

2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

Enabling multiple robots to collaboratively perform coverage path planning on complex surfaces embedded in R 3 with the presence of moving obstacles is a challenging problem that has not received much attention from researchers. As robots start to be practically deployed, it is becoming important to address this problem. A novel decentralized multirobot coverage path planning approach is proposed that is adaptive to unexpected stationary and moving obstacles while aiming to achieve complete coverage with minimal cost. The approach is inspired by the predator-prey relation. For a robot (a prey), a virtual stationary predator enforces spatial ordering on the prey, and dynamic predators (other robots) cause the prey to be repelled resulting in better task allocation and collision-avoidance. The approach makes the best use of both worlds: offline global planning for tuning of model parameters based on a prior map of the surface, and real-time local planning for adaptive and swift decision making amid moving obstacles and other robots while preserving global behavior. Comparisons with other approaches and extensive testing and validation using different number of robots, different surfaces and obstacles, and various scenarios are conducted.

show abstract

Section: A Case Study 1: Coverage Amid Stationary Obstaclesmentioning

confidence: 72%

Section: A Stationary Predator Avoidance Rewardmentioning

confidence: 99%

“…As such, the prey is given an extra reward for continuing motion in a straight direction. This reward function, which is similar to the work in [15], is formulated as follows:…”

Section: Smoothness Rewardmentioning

confidence: 99%

Section: A Computational Complexitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations