Learning to Fly via Deep Model-Based Reinforcement Learning

03/19/2020
by   Philip Becker-Ehmck, et al.
7

Learning to control robots without requiring 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 achieve human-like quadrotor control 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.

READ FULL TEXT

page 1

page 6

page 9

page 14

09/02/2020

Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning

Nonholonomic control is a candidate to control nonlinear systems with pa...
02/26/2020

Efficient reinforcement learning control for continuum robots based on Inexplicit Prior Knowledge

Compared to rigid robots that are often studied in reinforcement learnin...
07/08/2019

Data Efficient Reinforcement Learning for Legged Robots

We present a model-based framework for robot locomotion that achieves wa...
06/10/2020

Deep Drone Acrobatics

Performing acrobatic maneuvers with quadrotors is extremely challenging....
03/05/2019

Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future

In model-based reinforcement learning, the agent interleaves between mod...
12/03/2019

Dream to Control: Learning Behaviors by Latent Imagination

Learned world models summarize an agent's experience to facilitate learn...
05/13/2021

Policy Optimization in Bayesian Network Hybrid Models of Biomanufacturing Processes

Biopharmaceutical manufacturing is a rapidly growing industry with impac...