DiffTune: Auto-Tuning through Auto-Differentiation
Cheng, Sheng, Kim, Minkyung, Song, Lin, Yang, Chengyu, Jin, Yiquan, Wang, Shenlong, Hovakimyan, Naira
–arXiv.org Artificial Intelligence
The performance of robots in high-level tasks depends on the quality of their lower-level controller, which requires fine-tuning. However, the intrinsically nonlinear dynamics and controllers make tuning a challenging task when it is done by hand. In this paper, we present DiffTune, a novel, gradient-based automatic tuning framework. We formulate the controller tuning as a parameter optimization problem. Our method unrolls the dynamical system and controller as a computational graph and updates the controller parameters through gradient-based optimization. The gradient is obtained using sensitivity propagation, which is the only method for gradient computation when tuning for a physical system instead of its simulated counterpart. Furthermore, we use $\mathcal{L}_1$ adaptive control to compensate for the uncertainties (that unavoidably exist in a physical system) such that the gradient is not biased by the unmodelled uncertainties. We validate the DiffTune on a Dubin's car and a quadrotor in challenging simulation environments. In comparison with state-of-the-art auto-tuning methods, DiffTune achieves the best performance in a more efficient manner owing to its effective usage of the first-order information of the system. Experiments on tuning a nonlinear controller for quadrotor show promising results, where DiffTune achieves 3.5x tracking error reduction on an aggressive trajectory in only 10 trials over a 12-dimensional controller parameter space.
arXiv.org Artificial Intelligence
Aug-15-2023
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- United States
- Pennsylvania > Philadelphia County
- Philadelphia (0.04)
- New Jersey > Hudson County
- Hoboken (0.04)
- Nevada > Clark County
- Las Vegas (0.04)
- Illinois > Champaign County
- Urbana (0.04)
- Georgia > Fulton County
- Atlanta (0.04)
- Florida > Alachua County
- Gainesville (0.04)
- Pennsylvania > Philadelphia County
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- United States
- Europe
- Germany > Berlin (0.04)
- United Kingdom > England
- Greater London > London (0.04)
- Sweden > Stockholm
- Stockholm (0.04)
- Asia
- Oceania > Australia
- Genre:
- Research Report (0.63)
- Overview (0.46)
- Industry:
- Energy (0.46)
- Leisure & Entertainment > Games
- Computer Games (0.34)
- Technology:
- Information Technology > Artificial Intelligence
- Robots (1.00)
- Representation & Reasoning
- Optimization (0.48)
- Agents (0.46)
- Machine Learning
- Statistical Learning (0.68)
- Neural Networks > Deep Learning (0.46)
- Information Technology > Artificial Intelligence