Sample-Based Hybrid Mode Control: Asymptotically Optimal Switching of Algorithmic and Non-Differentiable Control Modes
Yilang Liu, Haoxiang You, Ian Abraham
AI summary
Problem
Agile robots must dynamically switch between discrete, non-differentiable, and algorithmic control modes, but traditional hybrid control methods struggle with the combinatorial complexity and lack of gradients, leading to instability and suboptimal performance.
Approach
The authors reformulate hybrid mode switching as a discrete-time integer optimization problem and solve it iteratively by uniformly sampling mode transition tuples (mode, start time, duration) to efficiently search the solution space without gradients or predefined schedules.
Key results
- Novel iterative sample-based formulation for hybrid mode sequencing
- Provable asymptotic convergence guarantees for mode optimization
- Successful synthesis of complex agile behaviors on a real-world quadruped
- Outperforms modern trajectory optimization in synchronizing complex hybrid modes
Why it matters
Enables reliable, high-performance control for agile robots in contact-rich environments, bridging theoretical hybrid control with practical robotic deployment.
Abstract
This paper investigates a sample-based solution to the hybrid mode control problem across non-differentiable and algorithmic hybrid modes. Our approach reasons about a set of hybrid control modes as an integer-based optimization problem where we select what mode to apply, when to switch to another mode, and the duration for which we are in a given control mode. A sample-based variation is derived to efficiently search the integer domain for optimal solutions. We find our formulation yields strong performance guarantees that can be applied to a number of robotics-related tasks. In addition, our approach is able to synthesize complex algorithms and policies to compound behaviors and achieve challenging tasks. Last, we demonstrate the effectiveness of our approach in a real-world robotic examples that requires reactive switching between long- term planning and high-frequency control. Videos are avail- able on https://yilangliu.github.io/hybrid_mode_ sampling/