Probabilistically-Safe Bipedal Navigation Over Uncertain Terrain Via Conformal Prediction and Contraction Analysis
Kasidit Muenprasitivej, Ye Zhao, Glen Chou
AI summary
Problem
Bipedal robots struggle to traverse rough, uncertain terrain due to instability from unpredictable elevation changes and unregulated centroidal momentum, while existing frameworks often lack low-level corrective control with formal confidence guarantees.
Approach
The authors combine Gaussian Process regression with Conformal Prediction to quantify terrain uncertainty, then feed these bounds into a high-level Model Predictive Control planner and a low-level contraction-based flywheel torque controller to guarantee safe, robust locomotion.
Key results
- Calibrated terrain elevation confidence intervals via GP regression and Conformal Prediction
- Uncertainty-informed MPC framework guaranteeing provably-safe center-of-mass planning
- Contraction-based flywheel torque controller maintaining trajectories within robust control invariant tubes
- Physics-based MuJoCo simulations validating safe navigation on the Digit robot
Why it matters
Enables reliable, theoretically guaranteed bipedal navigation in unstructured environments, bridging the gap between uncertainty-aware planning and dynamic low-level control.
Abstract
We address the challenge of enabling bipedal robots to traverse rough terrain by developing probabilistically safe planning and control strategies that ensure dynamic feasibility and centroidal robustness under terrain uncertainty. Specifically, we propose a high-level Model Predictive Control (MPC) navigation framework for a bipedal robot with a specified confidence level of safety that (i) enables safe traversal toward a desired goal location across a terrain map with uncertain elevations, and (ii) formally incorporates uncertainty bounds into the centroidal dynamics of locomotion control. To model the rough terrain, we employ Gaussian Process (GP) regression to estimate elevation maps and leverage Conformal Prediction (CP) to construct calibrated confidence intervals that capture the true terrain elevation. Building on this, we formulate contraction-based reachable tubes that explicitly account for terrain uncertainty, ensuring state convergence and tube invariance. In addition, we introduce a contraction- based flywheel torque control law for the reduced-order Linear Inverted Pendulum Model (LIPM), which stabilizes the angular momentum about the center-of-mass (CoM). This formula- tion provides both probabilistic safety and goal reachability guarantees. For a given confidence level, we establish the forward invariance of the proposed torque control law by demonstrating exponential stabilization of the actual CoM phase-space trajectory and the desired trajectory prescribed by the high-level planner. Finally, we evaluate the effectiveness of our planning framework through physics-based simulations of the Digit bipedal robot in MuJoCoi.