Albert Wilcox
@albertwilcoxiii
second year PhD student at Georgia Tech @ICatGT working on 3D scene representations and foundation models | MS from @berkeley_ai
Imitation learning has seen great success, but IL policies still struggle with OOD observations We designed a 3D backbone, Adapt3R, that can combine with your favorite IL algorithm to enable zero-shot generalization to unseen embodiments and camera viewpoints!
Great work from Jeremy and Lorand and a pleasure helping out with the paper! Do give it a read
Robotics data is expensive and slow to collect. Robotics labs and companies spend months just to collect around 10k hours of demonstration data, all while that much video is uploaded to YouTube every 20 minutes. However, none of this video data contains action labels. How can we…
Imitation learning frameworks are often with 2D inputs. but 2D limits generalization even to camera poses. This has been an ongoing challenge, especially for humanoids since the camera pose is not steady and need not match the training data. @albertwilcoxiii has been working on…
Tired of slow-moving robots? Want to know how learning-driven robots can move closer to industrial speeds in the real world? Introducing SAIL - a system for speeding up the execution of imitation learning policies up to 3.2x on real robots. A short thread: 1/
I am alarmed by the proposed cuts to U.S. funding for basic research, and the impact this would have for U.S. competitiveness in AI and other areas. Funding research that is openly shared benefits the whole world, but the nation it benefits most is the one where the research is…
Introducing EgoMimic - just wear a pair of Project Aria @meta_aria smart glasses 👓 to scale up your imitation learning datasets! Check out what our robot can do. A thread below👇
Excited to share our #NeurIPS2024 work on QueST: Self-Supervised Skill Abstractions for Learning Continuous Control🦾🤖 QueST is a multitask latent-variable model that learns sharable low-level skills and outperforms Diffusion Policy, ACT and VQ-BeT by >13% in 5-shot transfer.🧵
When building robotic systems, we create policies to make progress on our task. But what if we encounter states where attempting progress is challenging or risky? In our #ICRA2023 paper, we shape behavior in difficult parts of the state space for the task of untangling cables.