22 citations · 33 across the 6 of their papers we have counts for
7 papers
DIA: Denoising Intermediate Advantage for Diffusion Policy Optimization
Arjun Sohal, Yuchi Zhao, Miroslav Bogdanovic +1
Diffusion-based robot policies have become widely used in robotic manipulation, where they are typically trained with behavior cloning. However, policies trained purely from demons…
Dynamic Execution Horizon Prediction for Chunk-based Robot Policies
Yuchi Zhao, Miroslav Bogdanovic, Arjun Sohal +5
Action chunking has become a standard design in modern robot policies, from diffusion/flow policies to vision-language-action models, where the policy predicts a sequence of action…
MATTERIX: toward a digital twin for robotics-assisted chemistry laboratory automation
Kourosh Darvish, Arjun Sohal, Abhijoy Mandal +20
Accelerated materials discovery is critical for addressing global challenges. However, developing new laboratory workflows relies heavily on real-world experimental trials, and thi…
AnyPlace: Learning Generalized Object Placement for Robot Manipulation
Yuchi Zhao, Miroslav Bogdanovic, Chengyuan Luo +5
Object placement in robotic tasks is inherently challenging due to the diversity of object geometries and placement configurations. To address this, we propose AnyPlace, a two-stag…
CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Building
Walker Byrnes, Miroslav Bogdanovic, Avi Balakirsky +2
Intelligent and reliable task planning is a core capability for generalized robotics, requiring a descriptive domain representation that sufficiently models all object and state in…
Automated Planning Domain Inference for Task and Motion Planning
Jinbang Huang, Allen Tao, Rozilyn Marco +3
Task and motion planning (TAMP) frameworks address long and complex planning problems by integrating high-level task planners with low-level motion planners. However, existing TAMP…
ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization
Kourosh Darvish, Marta Skreta, Yuchi Zhao +9
Chemistry experiments can be resource- and labor-intensive, often requiring manual tasks like polishing electrodes in electrochemistry. Traditional lab automation infrastructure fa…