A Path Planning Learning Strategy Design for a Wheel-Legged Vehicle Considering Both Distance and Energy Consumption

To obtain an optimal feasible path, this paper presents a path planning learning strategy for a wheel-legged vehicle considering both distance and energy consumption. Firstly, a new reward function and update rule of the Q-Learning algorithm, considering the influence of obstacle crossing parameters and modification of path energy consumption, is presented to ensure the path shortening and energy consumption reduction. Secondly, the future energy consumption is introduced into the modification of path energy consumption. It evaluates the potential energy consumption between each state reached by the vehicle and the target state. The priority sequence of Q table update is provided, which greatly speeds up the convergence speed of the algorithm. Finally, the proposed strategy is verified on different size maps with 0-1m obstacle height. Results show that, in the complex map, the proposed strategy is effective to shorten 7.6m distance compared with the wheeled driving strategy and to reduce energy consumption by 31% compared with the wheel-legged obstacle crossing strategy. It has a faster convergence speed. Compared with the A*-based and Dijkstra-based strategies, their planning effect is approximately the same, but the energy consumption using the proposed strategy can be reduced by 3.5%.

Automated summary

In this paper, a path planning learning strategy is proposed for a wheel-legged vehicle considering distance and energy consumption. A new reward function and update rule of the Q-Learning algorithm are presented to ensure path shortening and energy consumption reduction. Furthermore, the future energy consumption is introduced into the modification of path energy consumption. The proposed strategy is verified on different size maps with 0-1m obstacle height, showing effective path shortening and energy consumption reduction compared to other strategies tested.