We present Timing-Aware Detachable-task planning (TAD), which converts an existing task plan into a timing-aware plan. TAD rearranges the plan based on detachable tasks and optimizes timing according to possible task combinations. To this end, it reformulates the sequential plan as a linear program (LP), enabling the derivation of optimal solutions.
@inproceedings{timing-aware-planning-iros2026,title={Efficient Timing-Aware Planning via Detachable Task Modeling},author={Kim, Seungmin and Park, Kisang and Jung, Ina and Kim, Hyeonseong and Park, Dongkyu and Lee, Yisoo and Lee, Inho and Oh, Yoonseon and Lee, Kyungjae and Choi, Sungjoon},booktitle={Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},year={2026},}
Learning Dexterous Grasping from Sparse Taxonomy Guidance
Juhan Park , Taerim Yoon , Seungmin Kim, and 10 more authors
In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2026
GRIT is a two-stage framework that learns dexterous grasping from sparse taxonomy guidance: it first predicts a taxonomy-based grasp specification from the scene and task, then a policy conditioned on this sparse command generates continuous multi-finger control. This keeps the controller steerable by users while avoiding dense pose or contact targets for every object and task.
@inproceedings{grasp-taxonomy-guidance-iros2026,title={Learning Dexterous Grasping from Sparse Taxonomy Guidance},author={Park, Juhan and Yoon, Taerim and Kim, Seungmin and Kim, Joonggil and Ye, Wontae and Park, Jeongeun and Chai, Yoonbyung and Cho, Geonwoo and Cho, Geunwoo and Kim, Dohyeong and Lee, Kyungjae and Kim, Yongjae and Choi, Sungjoon},booktitle={Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},year={2026},}
2025
Spatio-Temporal Motion Retargeting for Quadruped Robots
Taerim Yoon , Dongho Kang , Seungmin Kim, and 4 more authors
Our method enables terrain-aware motion retargeting and time-critical skills such as BackFlip and HopTurn from noisy inputs, including videos or physics-ignorant kinematic frames, and successfully deploys them on real robots.
@article{spatio-temporal-motion-retargeting-2025,title={Spatio-Temporal Motion Retargeting for Quadruped Robots},author={Yoon, Taerim and Kang, Dongho and Kim, Seungmin and Cheng, Jin and Ahn, Minsung and Coros, Stelian and Choi, Sungjoon},journal={IEEE Transactions on Robotics (T-RO)},year={2025},}