Search papers, labs, and topics across Lattice.
VISION-SLS enables safe nonlinear output-feedback control from high-resolution RGB images by combining learned low-dimensional observation maps with System Level Synthesis (SLS). The method optimizes a causal affine time-varying output-feedback policy while providing robust constraint satisfaction guarantees under uncertainty. Experiments on simulated and real-world visuomotor tasks demonstrate the method's ability to achieve safe, information-gathering behavior while outperforming baselines in safety rate and solve times.
Safe visuomotor control from high-resolution images is now practical at scale, thanks to a learned visual abstraction coupled with an efficient SLS solver.
We propose VISION-SLS, a method for nonlinear output-feedback control from high-resolution RGB images which provides robust constraint satisfaction guarantees under calibrated uncertainty bounds despite partial observability, sensor noise, and nonlinear dynamics. To enable scalability while retaining guarantees, we propose: (i) a learned low-dimensional observation map from pretrained visual features with state-dependent error bounds, and (ii) a causal affine time-varying output-feedback policy optimized via System Level Synthesis (SLS). We develop a scalable, novel solver for the resulting nonconvex program that leverages sequential convex programming coupled with efficient Riccati recursions. On two simulated visuomotor tasks (a 4D car and a 10D quadrotor) with>= 512 x 512 pixels and a 59D humanoid task with partial observability, our method enables safe, information-gathering behavior that reduces uncertainty while guaranteeing constraint satisfaction with empirically-calibrated error bounds. We also validate our method on hardware, safely controlling a ground vehicle from onboard images, outperforming baselines in safety rate and solve times. Together, these results show that learned visual abstractions coupled with an efficient solver make SLS-based safe visuomotor output-feedback practical at scale. The code implementation of our method is available at https://github.com/trustworthyrobotics/VISION-SLS.
