Optimal Path Planning Method for Robots Based on Partial Sensing Markov Decision Process

Abstract

The invention discloses a robot optimal path planning method based on partly perceived Markov decision-making process. The robot searches for the optimal path to the target position, based on the POMDP model and the SARSOP algorithm, and uses the GLS search method as the heuristic condition when searching. In the large-scale observation space problem of continuous state, the use of the present invention can prevent the early classic algorithm from repeatedly updating multiple similar paths based on experiments as heuristic conditions, and the number of times to update the upper and lower bounds of the belief state without affecting the final optimal strategy. Improve the efficiency of the algorithm. In the same time, the robot can train a better strategy and find a better path.

Description

technical field [0001] The invention relates to the field of robot control, in particular to a robot optimal path planning method based on a partially perceptual Markov decision process. Background technique [0002] Machine Learning (ML) is a discipline that studies how to simulate or realize human learning behavior, and constantly reorganize and improve its original knowledge structure. Reinforcement learning is an important research branch of machine learning. It is a machine learning method that maps state to action through the interaction between agent and environment, so as to obtain the maximum long-term cumulative discount reward. Usually reinforcement learning uses Markov Decision Processes (MDPs) as a model, that is, the environment is completely observable. In the real world, however, uncertainty is ubiquitous. For example, the agent's sensor has its own limitations: (1) the sensor can only detect local limited environments, and the agent cannot accurately disti...

AI Technical Summary

Problems solved by technology

However, the trial-based search selects the optimal action and observation each time, without considering other observations that are very close to the optimal observation and have a significant impact on future algorithm performance

In large-scale observation space problems, the performance of the algorithm is poor

Images