Studies from Tongji University Reveal New Findings on Robotics (Relaxing the Lim itations of the Optimal Reciprocal Collision Avoidance Algorithm for Mobile Robo ts In Crowds)
Studies from Tongji University Reveal New Findings on Robotics (Relaxing the Lim itations of the Optimal Reciprocal Collision Avoidance Algorithm for Mobile Robo ts In Crowds)
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – New research on Robotics is the subject of a repo rt. According to news reporting out of Shanghai, People’s Republic of China, by NewsRx editors, research stated, “The Optimal Reciprocal Collision Avoidance (OR CA) algorithm is widely used for modeling agents in collision avoidance scenario s. However, suffering from limitations such as the improper reciprocal assumptio n that each agent is supposed to take half the responsibility for collision avoi dance, the performance of ORCA-based mobile robots in crowds is not ideal.” Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news journalists obtained a quote from the research from Tongji University, “In this letter, to relax these limitations, we firstly simplify the planning pr ocess of ORCA from the principle horizon to solve ORCA being unsolvable in some cases. Then the escape velocity and collision avoidance responsibility are explo red simultaneously based on deep reinforcement learning (DRL) to solve the limit ation of local optimum caused by only exploring the responsibility in other work s. We compare our method with baselines in environments with different numbers o f pedestrians and test in different real-world scenarios.”
Key words
Shanghai/People’s Republic of China/As ia/Algorithms/Emerging Technologies/Machine Learning/Nano-robot/Robotics/T ongji University
NETL
NSTL