activity
20182026
most citedSemHint-MD: Learning from Noisy Semantic Labels for Self-Supervised Monocular Depth Estimation

1 citations · 1 across the 8 of their papers we have counts for

collaborators

7 papers

cs.LG2026

Learning More from Less: Reinforcement Learning from Hindsight

Iris Xu, Sunshine Jiang, John Marangola +8

Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, but every update consumes robot rollouts that are slow and costly to collect, ma…

cs.RO2026

Remember what you did?: Learning Behavioral Memories for Partially Observable Object Manipulation

Kuancheng Wang, Seungho Yeom, Jinglin Cao +3

Long horizon, contact-rich manipulation is inherently partially observable. This is as a single visual observation rarely captures a robot's full action context, including prior at…

cs.RO2026

SteadyTray: Learning Object Balancing Tasks in Humanoid Tray Transport via Residual Reinforcement Learning

Anlun Huang, Zhenyu Wu, Soofiyan Atar +2

Stabilizing unsecured payloads against the inherent oscillations of dynamic bipedal locomotion remains a critical engineering bottleneck for humanoids in unstructured environments.…

cs.RO2024

SurgIRL: Towards Life-Long Learning for Surgical Automation by Incremental Reinforcement Learning

Yun-Jie Ho, Zih-Yun Chiu, Yuheng Zhi +1

Surgical automation holds immense potential to improve the outcome and accessibility of surgery. Recent studies use reinforcement learning to learn policies that automate different…

cs.RO2024

KineDepth: Utilizing Robot Kinematics for Online Metric Depth Estimation

Soofiyan Atar, Yuheng Zhi, Florian Richter +1

Depth perception is essential for a robot's spatial and geometric understanding of its environment, with many tasks traditionally relying on hardware-based depth sensors like RGB-D…

cs.RO2021

Data-driven Actuator Selection for Artificial Muscle-Powered Robots

Taylor West Henderson, Yuheng Zhi, Angela Liu +1

Even though artificial muscles have gained popularity due to their compliant, flexible, and compact properties, there currently does not exist an easy way of making informed decisi…