A Pedestrian Sensing and Obstacle Avoidance Method for Service Robots Based on Deep Reinforcement Learning

Abstract

The invention discloses a service robot pedestrian perception obstacle avoidance method based on deep reinforcement learning, and relates to the fields of deep learning and service robot obstacle avoidance. The method is in the training phase: First, the ORCA algorithm is used to generate training data. Then, randomly generate experimental scenarios, use the initialized reinforcement learning model to interact with the environment to generate new training data, and integrate them into the original training data. Finally, use the SGD algorithm to train the network on the new training data to obtain the final network model. In the execution stage of this method: the state of the surrounding pedestrians is obtained through the lidar, the predicted state is calculated according to the trained model and the reward function, and the action that obtains the maximum reward is selected as the output and executed. The invention has strong real-time and adaptability, and can make the robot follow the pedestrian's right-going rule in the pedestrian environment, plan an efficient, safe and natural path, and improve the intelligence and sociality of the service robot.

Description

technical field [0001] The invention relates to the field of deep learning and obstacle avoidance of service robots, in particular to a pedestrian-aware obstacle avoidance method for service robots based on deep reinforcement learning. Background technique [0002] With the increase in labor costs, robots have begun to replace human workers in various fields, especially in the field of public services, such as takeaway robots, express delivery robots, shopping guide robots, etc. The scenes faced by these robots generally have many highly dynamic obstacles, such as pedestrians. How to enable service robots to navigate autonomously in a pedestrian environment and avoid pedestrian obstacles efficiently, safely and naturally has become a key issue that limits the wider application of service robots. In the pedestrian environment, the adaptability of the traditional obstacle avoidance algorithm becomes poor, and sometimes it will show unsafe behaviors such as sudden stop and sha...

AI Technical Summary

Problems solved by technology

[0006] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is to overcome the problem existing in the prior art that it is difficult to model the obstacle avoidance mechanism of pedestrians, and to overcome the end-to-end The training method is usually difficult to converge, or the convergence is very slow

Images