Multi-agent Approach for Low-cost Quadruped Robots Navigating on Uneven Terrains
摘要
The study presents a multi-agent approach for navigating low-cost quadruped robots with low sensing power across uneven terrain. This proposal is predicated on the concept that each paw of the multi-agent quadruped robot (MAQ-Robot) functions as an intelligent agent, capable of perceiving the environment and acting autonomously. Each agent is equipped with a time of flight (ToF) laser sensor at the foot’s end and receives data from an inertial measurement unit (IMU) module positioned at the robot’s center, facilitating decision-making. Several tests were conducted within a simulation environment to validate the efficiency of the proposed approach. The results demonstrate a significant enhancement in the navigation capabilities of quadruped robots on uneven terrains.