5 papers
Learning Robot Safety from Sparse Human Feedback using Conformal Prediction
Aaron O. Feldman, Joseph A. Vincent, Maximilian Adang +2
Ensuring robot safety can be challenging; user-defined constraints can miss edge cases, policies can become unsafe even when trained from safe data, and safety can be subjective. T…
GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics
Qianzhong Chen, Naixiang Gao, Suning Huang +4
Autonomous drones capable of interpreting and executing high-level language instructions in unstructured environments remain a long-standing goal. Yet existing approaches are const…
SINGER: An Onboard Generalist Vision-Language Navigation Policy for Drones
Maximilian Adang, JunEn Low, Ola Shorinwa +1
Large vision-language models have driven remarkable progress in open-vocabulary robot policies, e.g., generalist robot manipulation policies, that enable robots to complete complex…
GRaD-Nav: Efficiently Learning Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics
Qianzhong Chen, Jiankai Sun, Naixiang Gao +3
Autonomous visual navigation is an essential element in robot autonomy. Reinforcement learning (RL) offers a promising policy training paradigm. However existing RL methods suffer…
SOUS VIDE: Cooking Visual Drone Navigation Policies in a Gaussian Splatting Vacuum
JunEn Low, Maximilian Adang, Javier Yu +2
We propose a new simulator, training approach, and policy architecture, collectively called SOUS VIDE, for end-to-end visual drone navigation. Our trained policies exhibit zero-sho…