How to Train Your HERON

@article{Richard2021HowTT,
  title={How to Train Your HERON},
  author={Antoine Richard and St{\'e}phanie Aravecchia and Thomas Schillaci and Matthieu Geist and C{\'e}dric Pradalier},
  journal={IEEE Robotics and Automation Letters},
  year={2021},
  volume={6},
  pages={5247-5252}
}
In this letter we apply Deep Reinforcement Learning (Deep RL) and Domain Randomization to solve a navigation task in a natural environment relying solely on a 2D laser scanner. We train a model-based RL agent in simulation to follow lake and river shores and apply it on a real Unmanned Surface Vehicle in a zero-shot setup. We demonstrate that even though the agent has not been trained in the real world, it can fulfill its task successfully and adapt to changes in the robot's environment and… 

Figures and Tables from this paper

Learning Behaviors through Physics-driven Latent Imagination
TLDR
It is argued that decoupling the environment representation from the dynamics of the physical system can increase the ability of world models and open doors to greater robustness, and applied to a strong latent-agent, Dreamer.

References

SHOWING 1-10 OF 27 REFERENCES
Deep Reinforcement Learning: A Brief Survey
TLDR
This survey will cover central algorithms in deep RL, including the deep Q-network (DQN), trust region policy optimization (TRPO), and asynchronous advantage actor critic, and highlight the unique advantages of deep neural networks, focusing on visual understanding via RL.
(CAD)$^2$RL: Real Single-Image Flight without a Single Real Image
TLDR
This paper proposes a learning method that they call CAD$^2$RL, which can be used to perform collision-free indoor flight in the real world while being trained entirely on 3D CAD models, and shows that it can train a policy that generalizes to thereal world, without requiring the simulator to be particularly realistic or high-fidelity.
Domain randomization for transferring deep neural networks from simulation to the real world
TLDR
This paper explores domain randomization, a simple technique for training models on simulated images that transfer to real images by randomizing rendering in the simulator, and achieves the first successful transfer of a deep neural network trained only on simulated RGB images to the real world for the purpose of robotic control.
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.
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
TLDR
By randomizing the dynamics of the simulator during training, this paper is able to develop policies that are capable of adapting to very different dynamics, including ones that differ significantly from the dynamics on which the policies were trained.
Learning Latent Dynamics for Planning from Pixels
TLDR
The Deep Planning Network (PlaNet) is proposed, a purely model-based agent that learns the environment dynamics from images and chooses actions through fast online planning in latent space using a latent dynamics model with both deterministic and stochastic transition components.
Sim-to-Real: Learning Agile Locomotion For Quadruped Robots
TLDR
This system can learn quadruped locomotion from scratch using simple reward signals and users can provide an open loop reference to guide the learning process when more control over the learned gait is needed.
Reinforcement Learning with Augmented Data
TLDR
It is shown that augmentations such as random translate, crop, color jitter, patch cutout, random convolutions, and amplitude scale can enable simple RL algorithms to outperform complex state-of-the-art methods across common benchmarks.
High-Speed Autonomous Drifting With Deep Reinforcement Learning
TLDR
This work proposes a robust drift controller without explicit motion equations, which is based on the latest model-free deep reinforcement learning algorithm soft actor-critic, and is shown to have excellent generalization ability.
Reinforcement learning in robotics: A survey
TLDR
This article attempts to strengthen the links between the two research communities by providing a survey of work in reinforcement learning for behavior generation in robots by highlighting both key challenges in robot reinforcement learning as well as notable successes.
...
...