17 papers
InSight: Self-Guided Skill Acquisition via Steerable VLAs
Maggie Wang, Lars Osterberg, Stephen Tian +3
Vision-language-action (VLA) models can learn manipulation skills from demonstrations, but their capabilities are bounded by the skills in the training data. We present InSight, a…
Transformer-Based Warm-Starting for Feasible and Optimal Terminal Approach to Tumbling Objects with Space Manipulators
Yuji Takubo, Maximilian Adang, Mac Schwager +1
Real-time trajectory generation for on-orbit robotic servicing is challenging due to the nonlinear coupling between spacecraft bus motion, manipulator dynamics, visibility cone, an…
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…
Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models
Aiden Swann, Lachlain McGranahan, Hugo Buurmeijer +2
Vision-Language-Action (VLA) models have emerged as a promising approach for general-purpose robot manipulation. However, little research has mechanistically explored when and why…
Robots Need More than VLA and World Models
Elis Karcini, Faisal Mehrban, Quang Nguyen +6
Generalist robot intelligence is often framed as a policy-scaling problem: collect more robot demonstrations, train larger Vision-Language-Action (VLA) models, and expect broader g…
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…