Search papers, labs, and topics across Lattice.
This paper introduces a method for decoding latent representations from adaptive control policies into distributions of quadrotor models using conditional flow matching, addressing the challenge of interpreting internal policy latents. By enabling a direct mapping from latent variables to physical parameters, the approach facilitates online predictive tuning and robustness analysis without altering the underlying policy. The results demonstrate significant improvements in position tracking and heading accuracy under perturbed dynamics, showcasing the potential for enhanced control and diagnostic capabilities in robotic systems.
Control latents can be transformed into actionable physical model ensembles, leading to a 23% reduction in tracking error without changing the underlying policy.
Latent-conditioned adaptive policies can control robots across changing dynamics, but their learned latents remain internal representations of the policy rather than physical models that can be inspected, rolled out, or used by other control modules. This limits closed-loop analysis, diagnosis, and further improvement of a fixed policy. A direct mapping from latent to physical parameters is also under-specified, because multiple systems can induce similar closed-loop behavior. We therefore decode each operational latent into a distribution of quadrotor models using conditional flow matching. The decoded distribution enables two downstream uses without modifying the policy: online predictive tuning of a high-level controller around the fixed low-level policy, and robustness analysis under specified disturbances. Under perturbed actuator dynamics, decoded-model predictive tuning reduces position tracking RMSE by $23\%$ and heading RMSE by $45\%$ relative to fixed gains. Under Gaussian force disturbances, decoded-model ensembles closely predict the lateral tracking-error evolution. Together, these results show that control latents can be converted into physical model ensembles for tuning, robustness analysis, and diagnosis of frozen adaptive policies.
