TY - JOUR
T1 - Custom distribution for sampling-based motion planning
AU - Flores-Aquino, Gabriel O.
AU - Vasquez-Gomez, J. Irving
AU - Gutierrez-Frias, Octavio
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive licence to The Brazilian Society of Mechanical Sciences and Engineering.
PY - 2022/3
Y1 - 2022/3
N2 - Sampling-based motion planning algorithms are widely used in robotics because they are very effective in high-dimensional spaces. However, the success rate and quality of the solutions are determined by an adequate selection of their parameters such as the distance between states, the local planner, and the sampling distribution. For robots with large configuration spaces or dynamic restrictions, selecting these parameters is a challenging task. This paper proposes a method for improving the performance to a set of the most popular sampling-based algorithms, the Rapidly-exploring Random Trees (RRTs) by adjusting the sampling method. The idea is to replace the uniform probability density function (U-PDF) with a custom distribution (C-PDF) learned from previously successful queries in similar tasks. With a few samples, our method builds a custom distribution that allows the RRT to grow to promising states that will lead to a solution. We tested our method in several autonomous driving tasks such as parking maneuvers, obstacle clearance and under narrow passages scenarios. The results show that the proposed method outperforms the original RRT and several improved versions in terms of success rate, tree density and computation time. In addition, the proposed method requires a relatively small set of examples, unlike current deep learning techniques that require a vast amount of examples.
AB - Sampling-based motion planning algorithms are widely used in robotics because they are very effective in high-dimensional spaces. However, the success rate and quality of the solutions are determined by an adequate selection of their parameters such as the distance between states, the local planner, and the sampling distribution. For robots with large configuration spaces or dynamic restrictions, selecting these parameters is a challenging task. This paper proposes a method for improving the performance to a set of the most popular sampling-based algorithms, the Rapidly-exploring Random Trees (RRTs) by adjusting the sampling method. The idea is to replace the uniform probability density function (U-PDF) with a custom distribution (C-PDF) learned from previously successful queries in similar tasks. With a few samples, our method builds a custom distribution that allows the RRT to grow to promising states that will lead to a solution. We tested our method in several autonomous driving tasks such as parking maneuvers, obstacle clearance and under narrow passages scenarios. The results show that the proposed method outperforms the original RRT and several improved versions in terms of success rate, tree density and computation time. In addition, the proposed method requires a relatively small set of examples, unlike current deep learning techniques that require a vast amount of examples.
KW - Autonomous driving
KW - Autonomous parking
KW - Bias sampling
KW - RRT
KW - Sampling-based motion planning
UR - http://www.scopus.com/inward/record.url?scp=85124429092&partnerID=8YFLogxK
U2 - 10.1007/s40430-022-03379-0
DO - 10.1007/s40430-022-03379-0
M3 - Artículo
AN - SCOPUS:85124429092
SN - 1678-5878
VL - 44
JO - Journal of the Brazilian Society of Mechanical Sciences and Engineering
JF - Journal of the Brazilian Society of Mechanical Sciences and Engineering
IS - 3
M1 - 73
ER -