The Helping Hands Lab

The Helping Hands Lab

@Northeastern University

The Helping Hands Lab develops perception, planning, and control algorithms for robot manipulation in unstructured environments. We are particularly interested in robots that work with humans in built-for-human environments.

Publications

(2023). The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry. In ICLR 2023.

PDF Cite Video Website Talk

The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
(2023). Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction. In ICLR'23.

PDF Cite Website

Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction
(2023). A General Theory of Correct, Incorrect, and Extrinsic Equivariance. In Preprint.

PDF Cite

A General Theory of Correct, Incorrect, and Extrinsic Equivariance
(2023). SEIL: Simulation-augmented Equivariant Imitation Learning. In ICRA 2023.

PDF Cite Video Website

SEIL: Simulation-augmented Equivariant Imitation Learning
(2022). On-Robot Learning With Equivariant Models. In CoRL 2022.

PDF Cite Video Website

On-Robot Learning With Equivariant Models
(2022). Image to Icosahedral Projection for SO(3) Object Reasoning from Single-View Images. In PMLR.

PDF Cite Website

Image to Icosahedral Projection for SO(3) Object Reasoning from Single-View Images
(2022). Grasp Learning: Models, Methods, and Performance. In Annual Review of Control, Robotics, and Autonomous Systems, Vol 6.

PDF Cite

Grasp Learning: Models, Methods, and Performance
(2022). BulletArm: An Open-Source Robotic Manipulation Benchmark and Learning Framework. ISRR 2022.

PDF Cite Code Website

BulletArm: An Open-Source Robotic Manipulation Benchmark and Learning Framework
(2022). Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detection. In ICRA 2023.

PDF Cite Code Poster Website

Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detection
(2022). Leveraging Fully Observable Policies for Learning under Partial Observability. In CoRL 2022.

PDF Cite Code Website

Leveraging Fully Observable Policies for Learning under Partial Observability