We're pleased to announce that our workshop has been accepted as a full day workshop at ICRA 2019! Details to follow.
Legged robots are notoriously difficult to control. Recent progress in machine learning has shown promises to design robust and agile locomotion controllers automatically. However, most of these learning-based methods are limited to simulation or to simple hardware platforms. Many challenges remain in bringing these learning-based control approaches to real legged robots, including the reality gap, safe exploration, continuous data collection, data-efficient learning algorithms, experimental evaluation, and hardware robustness.
This workshop brings together experts in the fields of legged robotics and machine learning/reinforcement learning to discuss the state-of-the-art and challenges in learning-based control of legged robots.
Topics of Interest
Learning based control for legged locomotion:
- Reinforcement learning / evolutionary strategies
- Model based learning
- Learning in simulation
- On-robot learning
- Perception for unstructured terrain locomotion
- Sim-to-real transfer
- Hardware platforms for learning
- State estimation
09:00 - 09:10 Introduction
09:10 - 10:40 Session 1 (3 speakers)
10:40 - 11:10 Coffee break / Robot demos
11:10 - 12:40 Session 2 (3 speakers)
12:40 - 14:00 Lunch break
14:10 - 15:40 Session 3 (3 speakers)
15:40 - 16:20 Coffee break / Robot demos
16:20 - 17:00 Panel discussion