Boce Hu
@boce_hu
Followers
97
Following
123
Statuses
28
PhD student @HelpingHandsLab, @Northeastern, w/ @RobotPlatt. Robotics, learning and manipulation. Before @Columbia
Boston, MA
Joined November 2022
@Dian_Wang_ @corl_conf @tarikkelestemur @HaojieHuang13 @ZhaoHaibo47588 @RobinSFWalters @RobotPlatt Congrats!!! Dian!!
1
0
0
Equivariance is 🤫🤫🤫 Congrats @Dian_Wang_ 🐐🐐🐐
Honored to receive my first best paper nomination from @corl_conf! Had such a great time at #CoRL2024, huge thanks to the organizing committee and all my co-authors: Steve, David, @tarikkelestemur, @HaojieHuang13, @ZhaoHaibo47588, Mark, JW, @RobinSFWalters, @RobotPlatt!
1
0
0
Please come to the poster session! We are looking forward to seeing you! @Dian_Wang_ will help me present this project!
#CoRL2024 OrbitGrasp: SE(3)-Equivariant Grasp Learning Led by @boce_hu. Orbitgrasp maps each point in the cloud to a continuous grasp quality function using spherical harmonics. Our method outperforms all baselines across all settings and tasks. Presenting at Poster Session 1.
0
0
5
Please come to the session and talk with us!#CoRL2024
#CoRL2024 IMAGINATION POLICY: Using Generative Point Cloud Models for Learning Manipulation Policies Led by @HaojieHuang13. A key-frame multi-task policy can generate key poses (imagine) and do manipulation precisely with sample efficiency. Presenting at Poster Session 4.
0
0
4
RT @HelpingHandsLab: #CoRL2024 ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter by @RubyFreax. A plug-and-play v…
0
9
0
Please check our #CoRL2024 work!
#CoRL2024 Equivariant Diffusion Policy Led by @Dian_Wang_. A sample efficient BC algorithm based on equi diffusion. It leverages symmetry to boost learning with 5x less training data and mastering complex tasks with <60 demos. Presenting at Oral Session 1 and Poster Session 2.
0
0
5
RT @HelpingHandsLab: #CoRL2024 Leveraging Mutual Information for Asymmetric Learning under Partial Observability led by @HaiNguy69482974 Ad…
0
7
0
RT @Dian_Wang_: Check out our new grasping work, OrbitGrasp! It achieved a 98% grasping success rate by learning the SE(3)-equivariant gras…
0
8
0
Great question, the quantity comparison of the performance of our method with some off-the-shelf baselines is what we desperately want to know. We plan to do more general, reproducible real-world tasks to compare them. There are some real-world benchmarks that we can use for it.
@boce_hu Great work! Any idea how it compares to AnyGrasp or ContactGraspNet?
0
0
2
@davheld Great question, the quantity comparison of the performance of our method with some off-the-shelf baselines is what we desperately want to know. We plan to do more general, reproducible real-world tasks to compare them. There are some real-world benchmarks that we can use for it.
0
0
0
RT @chris_j_paxton: Grasping is one of those problems I just desperately want working out of the box solutions for
0
1
0
RT @YuXiang_IRVL: Nice work! We have a benchmark named SceneReplica for 6D grasping in the real world It would be…
0
3
0
Coauthors: @XupengZ, @Dian_Wang_, Zihao Dong, @HaojieHuang13, @330781570, @RobinSFWalters, @RobotPlatt. More details can be found in: Website: Paper: Video:
0
0
3