Layered Learning on a Physical Robot
نویسندگان
چکیده
Layered learning is a general hierarchical machine learning paradigm that leverages a given task decomposition to learn complex tasks efficiently. Though it has been validated previously in simulation, this paper presents the first application of layered learning on a physical robot. In particular, it enables the learning of a high-level grasping behavior that relies on a gait which itself must be learned. All learning is done autonomously onboard a commercially available Sony Aibo robot, with no human intervention other than battery changes. We demonstrate that our approach makes it possible to quickly learn both a fast gait and a reliable grasping behavior which, in combination, significantly outperform our best hand-tuned solution.
منابع مشابه
The Chin Pinch: A Case Study in Skill Learning on a Legged Robot
When developing skills on a physical robot, it is appealing to turn to modern machine learning methods in order to automate the process. However, when no accurate simulator exists for the type of motion in question, all learning must occur on the physical robot itself. In such a case, there is a high premium on quick, efficient learning (specifically, learning with low sample complexity). Recen...
متن کاملUT Austin Villa 2014: RoboCup 3D Simulation League Champion via Overlapping Layered Learning
Layered learning is a hierarchical machine learning paradigm that enables learning of complex behaviors by incrementally learning a series of sub-behaviors. A key feature of layered learning is that higher layers directly depend on the learned lower layers. In its original formulation, lower layers were frozen prior to learning higher layers. This paper considers an extension to the paradigm th...
متن کاملOverlapping layered learning
Layered learning is a hierarchical machine learning paradigm that enables learning of complex behaviors by incrementally learning a series of sub-behaviors. A key feature of layered learning is that higher layers directly depend on the learned lower layers. In its original formulation, lower layers were frozen prior to learning higher layers. This article considers a major extension to the para...
متن کاملLayered Learning for a Soccer Legged Robot Helped with a 3D Simulator
In the robotic soccer domain, many factors, such as the speed of individual robots, the effectiveness of kicks, and the choice of the appropriate attacking strategy, determine the success of a team. Consequently, soccer robots, and in particular legged ones, require fine tuning of the parameters not only for the vision processes, but also in the implementation of behaviors and basic control act...
متن کاملDynamic Obstacle Avoidance by Distributed Algorithm based on Reinforcement Learning (RESEARCH NOTE)
In this paper we focus on the application of reinforcement learning to obstacle avoidance in dynamic Environments in wireless sensor networks. A distributed algorithm based on reinforcement learning is developed for sensor networks to guide mobile robot through the dynamic obstacles. The sensor network models the danger of the area under coverage as obstacles, and has the property of adoption o...
متن کامل