6 papers
Exploring the Intrinsic Geometry of Diffusion Models with Constrained Inverse Kinematics
Miguel Angel Rogel Garcia, Phone Thiha Kyaw, Jonathan Kelly
Recent studies suggest that diffusion models can recover geometric structure in the data manifolds they are trained on, yet the supporting evidence has so far come mostly from natu…
Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples
Trevor Ablett, Bryan Chan, Jayce Haoran Wang +1
Common approaches to providing feedback in reinforcement learning are the use of hand-crafted rewards or full-trajectory expert demonstrations. Alternatively, one can use examples…
Learning Cross-Spectral Point Features with Task-Oriented Training
Mia Thomas, Trevor Ablett, Jonathan Kelly
Unmanned aerial vehicles (UAVs) enable operations in remote and hazardous environments, yet the visible-spectrum, camera-based navigation systems often relied upon by UAVs struggle…
Multimodal and Force-Matched Imitation Learning with a See-Through Visuotactile Sensor
Trevor Ablett, Oliver Limoyo, Adam Sigal +5
Contact-rich tasks continue to present many challenges for robotic manipulation. In this work, we leverage a multimodal visuotactile sensor within the framework of imitation learni…
PhotoBot: Reference-Guided Interactive Photography via Natural Language
Oliver Limoyo, Jimmy Li, Dmitriy Rivkin +2
We introduce PhotoBot, a framework for fully automated photo acquisition based on an interplay between high-level human language guidance and a robot photographer. We propose to co…
Working Backwards: Learning to Place by Picking
Oliver Limoyo, Abhisek Konar, Trevor Ablett +3
We present placing via picking (PvP), a method to autonomously collect real-world demonstrations for a family of placing tasks in which objects must be manipulated to specific, con…