6 papers
Good in Bad (GiB): Sifting Through End-user Demonstrations for Learning a Better Policy
Noushad Sojib, Ola Ghattas, Momotaz Begum
Imitation learning offers a promising framework for enabling robots to acquire diverse skills from human users. However, most imitation learning algorithms assume access to high-qu…
Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learning
Riad Ahmed, Sujosh Nag, Moniruzzaman Akash +2
Flow matching policies learn continuous velocity fields that transport noise to actions, enabling fast deterministic inference for robot manipulation. However, standard training op…
TAIL-Safe: Task-Agnostic Safety Monitoring for Imitation Learning Policies
Riad Ahmed, Momotaz Begum
Recent imitation learning (IL) algorithms such as flow-matching and diffusion policies demonstrate remarkable performance in learning complex manipulation tasks. However, these pol…
An Efficient Metric for Data Quality Measurement in Imitation Learning
Noushad Sojib, Momotaz Begum
Imitation learning (IL) has seen remarkable progress, yet field deployment of IL-powered robots remains hindered by the challenge of out-of-distribution (OOD) scenarios. Fine-tunin…
A Principled Approach for Creating High-fidelity Synthetic Demonstrations for Imitation Learning
Moniruzzaman Akash, Momotaz Begum
Recent advances in 3D Gaussian Splatting (3DGS) have enabled visually realistic demonstration generation from a single expert trajectory and a short multi-view scan. However, exist…
To Do or Not to Do: Ensuring the Safety of Visuomotor Policies Learned from Demonstrations
Riad Ahmed, Moniruzzaman Akash, Momotaz Begum
Task success has historically been the primary measure of policy performance in imitation learning (IL) research. This characteristics strictly limits the ubiquitous applications o…