11 papers
Sling2Sim2Real: One-Shot Elastic System Identification for Non-Destructive Slingshot Policy Learning
Wonjae Kang, Geonwoo Kim, Minseok Song +1
Elastic object manipulation (EOM) involves highdimensional, nonlinear, and elastic deformations. The diverse deformation properties of elastic objects substantially expand the rele…
ParCo-SDF: Learning Prior-Free Partial-to-Complete Signed Distance Fields of Deformable Objects
Deokmin Hwang, Minseok Song, Daehyung Park
This study addresses the partial-to-complete geometry reconstruction of deformable objects (DOs) from point-cloud observations toward precise DO manipulation. Recent DO reconstruct…
Dynamic Full-body Motion Agent with Object Interaction via Blending Pre-trained Modular Controllers
Sanghyeok Nam, Byoungjun Kim, Daehyung Park +1
Generating physically plausible dynamic motions of human-object interaction (HOI) remains challenging, mainly due to existing HOI datasets limited to static interactions, and pretr…
A Visuo-Tactile Data Collection System with Haptic Feedback for Coarse-to-Fine Imitation Learning
Yeseung Kim, Nayoung Oh, Jun Park +2
We present a visuo-tactile data-collection system that generates temporally structured, contact-rich demonstrations for imitation learning. Conventional systems often decouple the…
SuReNav: Superpixel Graph-based Constraint Relaxation for Navigation in Over-constrained Environments
Keonyoung Koh, Moonkyeong Jung, Samuel Seungsup Lee +1
We address the over-constrained planning problem in semi-static environments. The planning objective is to find a best-effort solution that avoids all hard constraint regions while…
C2F-Space: Coarse-to-Fine Space Grounding for Spatial Instructions using Vision-Language Models
Nayoung Oh, Dohyun Kim, Junhyeong Bang +2
Space grounding refers to localizing a set of spatial references described in natural language instructions. Traditional methods often fail to account for complex reasoning -- such…
ILCL: Inverse Logic-Constraint Learning from Temporally Constrained Demonstrations
Minwoo Cho, Jaehwi Jang, Daehyung Park
We aim to solve the problem of temporal-constraint learning from demonstrations to reproduce demonstration-like logic-constrained behaviors. Learning logic constraints is challengi…
Implicit Neural-Representation Learning for Elastic Deformable-Object Manipulations
Minseok Song, JeongHo Ha, Bonggyeong Park +1
We aim to solve the problem of manipulating deformable objects, particularly elastic bands, in real-world scenarios. However, deformable object manipulation (DOM) requires a policy…
DiSPo: Diffusion-SSM based Policy Learning for Coarse-to-Fine Action Discretization
Nayoung Oh, Jaehyeong Jang, Moonkyeong Jung +1
We aim to solve the problem of generating coarse-to-fine skills learning from demonstrations (LfD). To scale precision, traditional LfD approaches often rely on extensive fine-grai…
LINGO-Space: Language-Conditioned Incremental Grounding for Space
Dohyun Kim, Nayoung Oh, Deokmin Hwang +1
We aim to solve the problem of spatially localizing composite instructions referring to space: space grounding. Compared to current instance grounding, space grounding is challengi…
Inverse Constraint Learning and Generalization by Transferable Reward Decomposition
Jaehwi Jang, Minjae Song, Daehyung Park
We present the problem of inverse constraint learning (ICL), which recovers constraints from demonstrations to autonomously reproduce constrained skills in new scenarios. However,…