梦想
车轮运转
汽车工程
计算机科学
工程类
心理学
神经科学
内分泌学
医学
作者
Daniel Eriksson,Reza Ghabcheloo,Marcus Geimer
标识
DOI:10.1016/j.autcon.2024.105804
摘要
Reinforcement Learning (RL) requires many interactions with the environment to converge to an optimal strategy, which makes it unfeasible to apply to wheel loaders and the bucket filling problem without using simulators. However, it is difficult to model the pile dynamics in the simulator because of unknown parameters, which results in poor transferability from the simulation to the real environment. Instead, this paper uses world models, serving as a fast surrogate simulator, creating a dream environment where a reinforcement learning (RL) agent explores and optimizes its bucket-filling behavior. The trained agent is then deployed on a full-size wheel loader without modifications, demonstrating its ability to outperform the previous benchmark controller, which was synthesized using imitation learning. Additionally, the same performance was observed as that of a controller pre-trained with imitation learning and optimized on the test pile using RL. • Created a fast simulator for the bucket filling problem using world models and data from operators. • Optimized a controller in the fast simulator and deployed it directly to the machine. • The optimized controller outperformed benchmark methods in a field-test.
科研通智能强力驱动
Strongly Powered by AbleSci AI