2024 · 12 citations · 24 references
EngineeringComputer ScienceRobotics EngineeringMachine LearningRobot LearningRoboticsData-efficient Robot LearningLearning From DemonstrationManipulation LearningPolicy LearningReinforcement LearningRobot ManipulationDeep Reinforcement LearningPartial ObservabilityPeg-in-hole AssemblyPeg-in-hole ControlReinforcement Learning For RoboticsRobotic AssemblySample EfficiencySample-efficient Robot Learning
This study tackles the representative yet challenging contact-rich peg-in-hole task of robotic assembly, using a soft wrist that can operate more safely and tolerate lower-frequency control signals than a rigid one. Previous studies often use a fully observable formulation, requiring external setups or estimators for the peg-to-hole pose. In contrast, we use a partially observable formulation and deep reinforcement learning from demonstrations to learn a memory-based agent that acts purely on haptic and proprioceptive signals. Moreover, previous works do not incorporate potential domain symmetry and thus must search for solutions in a bigger space. Instead, we propose to leverage the symmetry for sample efficiency by augmenting the training data and constructing auxiliary losses to force the agent to adhere to the symmetry. Results in simulation with five different symmetric peg shapes show that our proposed agent can be comparable to or even outperform a state-based agent. In particular, the sample efficiency also allows us to learn directly on the real robot within 3 hours.
24
MuJoCo: A physics engine for model-based control
Emanuel Todorov, Tom Erez, Yuval Tassa · 2012 · 4.4K citations
Engineering, Mechanical Engineering, Robotics Engineering +17
Öncay Yaşa, Yasunori Toshimitsu, Mike Y. Michelis et al. · Annual Review of Control Robotics and Autonomous Systems · 2022 · 238 citations · Full text