논문Learning 분야의 논문·뉴스·데모를 모았습니다. 짧은 요약과 원문 링크를 함께 제공하며, 공개된 결과와 확인되지 않은 주장을 구분합니다.
논문
이 논문은 모델의 감각 표현을 말단 작동기 궤적으로 나타낸 물리적 운동의 기하학과 비교하는, 학습이 필요 없는 오프라인 지표인 감각운동 정렬(S²)을 제안한다. 12개의 비전-언어-행동 모델에서 S²는 후속 로봇 작업의 성공률과 양의 상관관계를 보인다. 저자들은 이를 미세 조정이나 비용이 많이 드는 폐루프 평가에 앞서 모델의 우선순위를 정하고 유망한 비전-언어 백본을 식별하는 저비용 방법으로 제시한다.
arXiv논문
SCOPE is an automated framework for generating diverse, executable task-and-motion-planning datasets for robots. It uses planner execution failures to correct logical inconsistencies in scene graphs, aiming to ensure plans are physically feasible. In experiments, data generated by SCOPE improved a fine-tuned downstream TAMP model’s success rate by an absolute 12.33% over a counterpart trained on DELTA-generated data.
arXiv cs.RO논문
The paper tests whether a Transformer can learn useful robot-action priors from procedurally generated data based on mathematical abstractions of control, without seeing real robot behavior during pretraining. The model achieves non-trivial zero-shot action prediction on unseen physical robot tasks through in-context learning; specialized control priors outperform generic causal priors. A compute-matched model trained on real robot data performs better only on the datasets it saw during training.
arXiv cs.RO뉴스
Dream Labs announced $90 million in seed funding and launched Dream API, which it says converts a robot camera feed and plain-English instructions into motor commands. Its Dream-1 model is trained on video of people performing everyday tasks and is claimed to transfer across robot hardware without robot-specific data. The company says it currently handles tabletop tasks, including picking and placing objects and folding laundry.
The Robot Report뉴스
The roundup highlights Workhorse, a system that learns contact-rich whole-body manipulation from human demonstrations without requiring a robot during demonstration. On a real Unitree G1, it sorts boxes using its hands and a kick, catches a thrown box, and topples and climbs a suitcase. The article also features MIT’s SANDO navigation system and a soft underwater robot with three swimming modes.
IEEE Spectrum데모
The video announces the open-source release of Unitree's UnifoLM-WLA-1.0 embodied foundation model, described as coordinating desktop and whole-body mobile manipulation.
Unitree Robotics