Research on path planning of autonomous vehicle based on RRT algorithm of Q-learning and obstacle distribution

Abstract

PurposeThe goal of this research is to develop a dynamic step path planning algorithm based on the rapidly exploring random tree (RRT) algorithm that combines Q-learning with the Gaussian distribution of obstacles. A route for autonomous vehicles may be swiftly created using this algorithm.Design/methodology/approachThe path planning issue is divided into three key steps by the authors. First, the tree expansion is sped up by the dynamic step size using a combination of Q-learning and the Gaussian distribution of obstacles. The invalid nodes are then removed from the initially created pathways using bidirectional pruning. B-splines are then employed to smooth the predicted pathways.FindingsThe algorithm is validated using simulations on straight and curved highways, respectively. The results show that the approach can provide a smooth, safe route that complies with vehicle motion laws.Originality/valueAn improved RRT algorithm based on Q-learning and obstacle Gaussian distribution (QGD-RRT) is proposed for the path planning of self-driving vehicles. Unlike previous methods, the authors use Q-learning to steer the tree's development direction. After that, the step size is dynamically altered following the density of the obstacle distribution to produce the initial path rapidly and cut down on planning time even further. In the aim to provide a smooth and secure path that complies with the vehicle kinematic and dynamical restrictions, the path is lastly optimized using an enhanced bidirectional pruning technique.

Recent advances in Rapidly-exploring random tree: A review

“…In Ref. [ 67 ], the step size varies according to the density of obstacle distribution and Q-learning is used to reduce the randomness of RRT, a scenario that no longer requires accurate environment modelling and vehicle modelling. In Refs.…”

Research on Path Planning and Path Tracking Control of Autonomous Vehicles Based on Improved APF and SMC

“…This study uses an exponential function to generate the external repulsion field. By calculating the negative derivative of the repulsive field function, the boundary repulsive force exerted by the road can be obtained, as represented in Equation (10).…”

“…It encompasses three main components, including environmental perception [ 4 ], path planning [ 5 ], and tracking control [ 6 ]. The first part relies on various sensors to detect the external environment and input this information into the autonomous vehicle system [ 7 , 8 , 9 ], thereby establishing the foundation for subsequent planning and control [ 10 ]. The objective of planning is to determine the most optimized path for intelligent vehicles using appropriate algorithms [ 11 ].…”

An efficient constraint method for solving planning problems under end-effector constraints

“…Sample-based planning is commonly acknowledged to sustain optimal performance in high-dimensional spaces (Choset et al, 2005). This strategy bypasses the need to compute the entire free CS by verifying each sampling point's validity (Shang et al, 2023). However, conducting direct sampling of valid configurations is usually unfeasible because manifolds are implicitly defined by constraints and lack analytical formulas (Palleschi et al, 2022;Kingston and Kavraki, 2023).…”