Dynamic path planning over CG-Space of 10DOF Rover with static and randomly moving obstacles using RRT* rewiring

Dynamic path planning is a core research content for intelligent robots. This paper presents a CG-Space-based dynamic path planning and obstacle avoidance algorithm for 10 DOF wheeled mobile robot (Rover) traversing over 3D uneven terrains. CG-Space is the locus of the center of gravity location of Rover while moving on a 3D terrain. A CG-Space-based modified RRT* samples a random space tree structure. Dynamic rewiring this tree can handle the randomly moving obstacles and target in real time. Simulations demonstrate that the Rover can obtain the target location in 3D uneven dynamic environments with fixed and randomly moving obstacles.

Research on Dynamic Path Planning of Mobile Robot Based on Improved DDPG Algorithm

Aiming at the problems of low success rate and slow learning speed of the DDPG algorithm in path planning of a mobile robot in a dynamic environment, an improved DDPG algorithm is designed. In this article, the RAdam algorithm is used to replace the neural network optimizer in DDPG, combined with the curiosity algorithm to improve the success rate and convergence speed. Based on the improved algorithm, priority experience replay is added, and transfer learning is introduced to improve the training effect. Through the ROS robot operating system and Gazebo simulation software, a dynamic simulation environment is established, and the improved DDPG algorithm and DDPG algorithm are compared. For the dynamic path planning task of the mobile robot, the simulation results show that the convergence speed of the improved DDPG algorithm is increased by 21%, and the success rate is increased to 90% compared with the original DDPG algorithm. It has a good effect on dynamic path planning for mobile robots with continuous action space.

Hardware-in-the-Loop Simulation of Self-Driving Electric Vehicles by Dynamic Path Planning and Model Predictive Control

This paper applies a dynamic path planning and model predictive control (MPC) to simulate self-driving and parking for an electric van on a hardware-in-the-loop (HiL) platform. The hardware platform is a simulator which consists of an electric power steering system, accelerator and brake pedals, and an Nvidia drive PX2 with a robot operating system (ROS). The vehicle dynamics model, sensors, controller, and test field map are virtually built with the PreScan simulation platform. Both manual and autonomous driving modes can be simulated, and a graphic user interface allows a test driver to select a target parking space on a display screen. Three scenarios are demonstrated: forward parking, reverse parking, and obstacle avoidance. When the vehicle perceives an obstacle, the map is updated and the route is adaptively planned. The effectiveness of the proposed MPC is verified in experiments and proved to be superior to a traditional proportional–integral–derivative controller with regards to safety, energy-saving, comfort, and agility.