Learning to Fly via Deep Model-Based Reinforcement Learning
- URL: http://arxiv.org/abs/2003.08876v3
- Date: Tue, 4 Aug 2020 10:41:38 GMT
- Title: Learning to Fly via Deep Model-Based Reinforcement Learning
- Authors: Philip Becker-Ehmck, Maximilian Karl, Jan Peters, Patrick van der
Smagt
- Abstract summary: We learn a thrust-attitude controller for a quadrotor through model-based reinforcement learning.
We show that "learning to fly" can be achieved with less than 30 minutes of experience with a single drone.
- Score: 37.37420200406336
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Learning to control robots without requiring engineered models has been a
long-term goal, promising diverse and novel applications. Yet, reinforcement
learning has only achieved limited impact on real-time robot control due to its
high demand of real-world interactions. In this work, by leveraging a learnt
probabilistic model of drone dynamics, we learn a thrust-attitude controller
for a quadrotor through model-based reinforcement learning. No prior knowledge
of the flight dynamics is assumed; instead, a sequential latent variable model,
used generatively and as an online filter, is learnt from raw sensory input.
The controller and value function are optimised entirely by propagating
stochastic analytic gradients through generated latent trajectories. We show
that "learning to fly" can be achieved with less than 30 minutes of experience
with a single drone, and can be deployed solely using onboard computational
resources and sensors, on a self-built drone.
Related papers
- Learning to enhance multi-legged robot on rugged landscapes [7.956679144631909]
Multi-legged robots offer a promising solution forNavigating rugged landscapes.
Recent studies have shown that a linear controller can ensure reliable mobility on challenging terrains.
We develop a MuJoCo-based simulator tailored to this robotic platform and use the simulation to develop a reinforcement learning-based control framework.
arXiv Detail & Related papers (2024-09-14T15:53:08Z) - BiRoDiff: Diffusion policies for bipedal robot locomotion on unseen terrains [0.9480364746270075]
Locomotion on unknown terrains is essential for bipedal robots to handle novel real-world challenges.
We introduce a lightweight framework that learns a single walking controller that yields locomotion on multiple terrains.
arXiv Detail & Related papers (2024-07-07T16:03:33Z) - Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for
Autonomous Real-World Reinforcement Learning [58.3994826169858]
We introduce RoboFuME, a reset-free fine-tuning system for robotic reinforcement learning.
Our insights are to utilize offline reinforcement learning techniques to ensure efficient online fine-tuning of a pre-trained policy.
Our method can incorporate data from an existing robot dataset and improve on a target task within as little as 3 hours of autonomous real-world experience.
arXiv Detail & Related papers (2023-10-23T17:50:08Z) - End-to-End Reinforcement Learning for Torque Based Variable Height
Hopping [5.34772724436823]
Legged locomotion is arguably the most suited and versatile mode to deal with natural or unstructured terrains.
In this paper, we present a end-to-end RL based torque controller that learns to implicitly detect the relevant jump phases.
We also extend a method for simulation to reality transfer of the learned controller to contact rich dynamic tasks, resulting in successful deployment on the robot.
arXiv Detail & Related papers (2023-07-31T13:51:29Z) - Learning and Adapting Agile Locomotion Skills by Transferring Experience [71.8926510772552]
We propose a framework for training complex robotic skills by transferring experience from existing controllers to jumpstart learning new tasks.
We show that our method enables learning complex agile jumping behaviors, navigating to goal locations while walking on hind legs, and adapting to new environments.
arXiv Detail & Related papers (2023-04-19T17:37:54Z) - Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement
Learning [54.636562516974884]
In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on.
In this work, we propose MEDAL++, a novel design for self-improving robotic systems.
The robot autonomously practices the task by learning to both do and undo the task, simultaneously inferring the reward function from the demonstrations.
arXiv Detail & Related papers (2023-03-02T18:51:38Z) - Real-to-Sim: Predicting Residual Errors of Robotic Systems with Sparse
Data using a Learning-based Unscented Kalman Filter [65.93205328894608]
We learn the residual errors between a dynamic and/or simulator model and the real robot.
We show that with the learned residual errors, we can further close the reality gap between dynamic models, simulations, and actual hardware.
arXiv Detail & Related papers (2022-09-07T15:15:12Z) - An Adaptable Approach to Learn Realistic Legged Locomotion without
Examples [38.81854337592694]
This work proposes a generic approach for ensuring realism in locomotion by guiding the learning process with the spring-loaded inverted pendulum model as a reference.
We present experimental results showing that even in a model-free setup, the learned policies can generate realistic and energy-efficient locomotion gaits for a bipedal and a quadrupedal robot.
arXiv Detail & Related papers (2021-10-28T10:14:47Z) - Reinforcement Learning for Robust Parameterized Locomotion Control of
Bipedal Robots [121.42930679076574]
We present a model-free reinforcement learning framework for training robust locomotion policies in simulation.
domain randomization is used to encourage the policies to learn behaviors that are robust across variations in system dynamics.
We demonstrate this on versatile walking behaviors such as tracking a target walking velocity, walking height, and turning yaw.
arXiv Detail & Related papers (2021-03-26T07:14:01Z) - Learning to Fly -- a Gym Environment with PyBullet Physics for
Reinforcement Learning of Multi-agent Quadcopter Control [0.0]
We propose an open-source environment for multiple quadcopters based on the Bullet physics engine.
Its multi-agent and vision based reinforcement learning interfaces, as well as the support of realistic collisions and aerodynamic effects, make it, to the best of our knowledge, a first of its kind.
arXiv Detail & Related papers (2021-03-03T02:47:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.