Evolving a Behavioral Repertoire for a Walking Robot
Evolving a Behavioral Repertoire for a Walking Robot
复制标题
DOI：
10.1162/evco_a_00143
复制
发表时间：
2016-03-01
影响因子：
6.8
通讯作者：
Mouret, J. -B.
中科院分区：
文献类型：
--
作者：
Cully, A.;Mouret, J. -B.
已经提出了许多算法来允许腿式机器人学习走路。然而，这些算法中的大多数被设计为学习直线行走，这不足以完成任何现实世界的使命。在这里，我们介绍了基于可转移性的行为库进化算法（TBR-Evolution），一种新的进化算法，同时发现了数百个简单的行走控制器，每个可能的方向。通过利用通常被进化过程丢弃的解决方案，TBR-Evolution比独立进化每个控制器要快得多。我们的技术依赖于两种方法：（1）新奇搜索与本地竞争，搜索高性能和多样化的解决方案，和（2）可转移性的方法，它结合了模拟和真实的测试，以发展控制器的物理机器人。我们在六足机器人上评估了这项新技术。结果表明，只需在机器人上进行几十个简短的实验，该算法就可以学习一系列控制器，使机器人能够到达其可达空间中的每一个点。总的来说，TBR-Evolution引入了一种新的学习算法，可以同时优化机器人所有可实现的行为。
Numerous algorithms have been proposed to allow legged robots to learn to walk. However, most of these algorithms are devised to learn walking in a straight line, which is not sufficient to accomplish any real-world mission. Here we introduce the Transferability-based Behavioral Repertoire Evolution algorithm (TBR-Evolution), a novel evolutionary algorithm that simultaneously discovers several hundreds of simple walking controllers, one for each possible direction. By taking advantage of solutions that are usually discarded by evolutionary processes, TBR-Evolution is substantially faster than independently evolving each controller. Our technique relies on two methods: (1) novelty search with local competition, which searches for both high-performing and diverse solutions, and (2) the transferability approach, which combines simulations and real tests to evolve controllers for a physical robot. We evaluate this new technique on a hexapod robot. Results show that with only a few dozen short experiments performed on the robot, the algorithm learns a repertoire of controllers that allows the robot to reach every point in its reachable space. Overall, TBR-Evolution introduced a new kind of learning algorithm that simultaneously optimizes all the achievable behaviors of a robot.