Corpus ID: 221640622

Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning

@inproceedings{Charlesworth2021SolvingCD,
  title={Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning},
  author={Henry Charlesworth and G. Montana},
  booktitle={ICML},
  year={2021}
}
Training agents to autonomously learn how to use anthropomorphic robotic hands has the potential to lead to systems capable of performing a multitude of complex manipulation tasks in unstructured and uncertain environments. In this work, we first introduce a suite of challenging simulated manipulation tasks that current reinforcement learning and trajectory optimisation techniques find difficult. These include environments where two simulated hands have to pass or throw objects between each… Expand
1 Citations

Figures from this paper

Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation
TLDR
This work presents benchmarks for the TriFinger system, an open-source robotic platform for dexterous manipulation and the focus of the 2020 Real Robot Challenge, and describes the benchmarked methods as structured policies. Expand

References

SHOWING 1-10 OF 27 REFERENCES
Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
TLDR
This work shows that model-free DRL with natural policy gradients can effectively scale up to complex manipulation tasks with a high-dimensional 24-DoF hand, and solve them from scratch in simulated experiments. Expand
Learning dexterous manipulation for a soft robotic hand from human demonstrations
TLDR
An approach to learning from demonstration is described that can be used to train soft robotic hands to perform dexterous manipulation tasks and is proposed with an extension of the guided policy search framework that learns generalizable neural network policies. Expand
Deep Dynamics Models for Learning Dexterous Manipulation
TLDR
It is shown that improvements in learned dynamics models, together with improvements in online model-predictive control, can indeed enable efficient and effective learning of flexible contact-rich dexterous manipulation skills -- and that too, on a 24-DoF anthropomorphic hand in the real world, using just 4 hours of purely real-world data to learn to simultaneously coordinate multiple free-floating objects. Expand
Overcoming Exploration in Reinforcement Learning with Demonstrations
TLDR
This work uses demonstrations to overcome the exploration problem and successfully learn to perform long-horizon, multi-step robotics tasks with continuous control such as stacking blocks with a robot arm. Expand
Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
TLDR
A suite of challenging continuous control tasks (integrated with OpenAI Gym) based on currently existing robotics hardware and following a Multi-Goal Reinforcement Learning (RL) framework are introduced. Expand
Learning dexterous in-hand manipulation
TLDR
This work uses reinforcement learning (RL) to learn dexterous in-hand manipulation policies that can perform vision-based object reorientation on a physical Shadow Dexterous Hand, and these policies transfer to the physical robot despite being trained entirely in simulation. Expand
Goal-conditioned Imitation Learning
TLDR
Different approaches to incorporate demonstrations to drastically speed up the convergence to a policy able to reach any goal, also surpassing the performance of an agent trained with other Imitation Learning algorithms are investigated. Expand
Real-time behaviour synthesis for dynamic hand-manipulation
TLDR
This work demonstrates for the first time online planning (or model-predictive control) with a full physics model of a humanoid hand, with 28 degrees of freedom and 48 pneumatic actuators, and augment the actuation space with motor synergies which speed up optimization without removing dexterity. Expand
Continuous control with deep reinforcement learning
TLDR
This work presents an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces, and demonstrates that for many of the tasks the algorithm can learn policies end-to-end: directly from raw pixel inputs. Expand
Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
TLDR
A general and model-free approach for Reinforcement Learning on real robotics with sparse rewards built upon the Deep Deterministic Policy Gradient algorithm to use demonstrations that out-performs DDPG, and does not require engineered rewards. Expand
...
1
2
3
...