Five papers accepted to IROS 2026!

The CoMMA Lab will be presenting seven papers at IROS 2026!

“Vectorizing Projection in Manifold-Constrained Motion Planning for Real-Time Whole-Body Control” with Shrutheesh Raman Iyer, I-Chia Chang, Andrew Liu, and Yan Gu

“HJCD-IK: GPU-Accelerated Inverse Kinematics through Batched Hybrid Jacobian Coordinate Descent” with Cael Yasutake, Andrew H. Liu, and Brian Plancher

“CDE: Concept-Driven Exploration for Reinforcement Learning” with Le Mao, Andrew H. Liu, Renos Zabounidis, and Joseph Campbell

“NeHMO: Neural Hamilton-Jacobi Reachability Learning for Decentralized Safe Multi-Arm Motion Planning” with Qingyi Chen and Ahmed H. Qureshi

“Fast Asymptotically Optimal Kinodynamic Planning via Vectorization” with Yitian Gao and Andrew Lu

We will also be presenting two RA-L papers:

“Efficient Multi-Robot Motion Planning for Manifold-Constrained Manipulators by Randomized Scheduling and Informed Path Generation” with Weihang Guo, Kaiyu Hang, and Lydia E. Kavraki

“Variational Shape Inference for Grasp Diffusion on SE(3)” with S. Talha Bukhari, Kaivalya Agrawal, and Aniket Bera