11 papers
Reducing Oracle Feedback with Vision-Language Embeddings for Preference-Based RL
Udita Ghosh, Dripta S. Raychaudhuri, Jiachen Li +2
Preference-based reinforcement learning can learn effective reward functions from comparisons, but its scalability is constrained by the high cost of oracle feedback. Lightweight v…
Toward Autonomous Laboratory Safety Monitoring with Vision Language Models: Learning to See Hazards Through Scene Structure
Trishna Chakraborty, Udita Ghosh, Aldair Ernesto Gongora +5
Laboratories are prone to severe injuries from minor unsafe actions, yet continuous safety monitoring -- beyond mandatory pre-lab safety training -- is limited by human availabilit…
Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation
Sarosij Bose, Ravi K. Rajendran, Biplob Debnath +3
Radiology Report Generation (RRG) is a critical step toward automating healthcare workflows, facilitating accurate patient assessments, and reducing the workload of medical profess…
Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling
Jianpeng Yao, Xiaopan Zhang, Yu Xia +3
Mobile robots navigating in crowds trained using reinforcement learning are known to suffer performance degradation when faced with out-of-distribution scenarios. We propose that b…
Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation
Sarosij Bose, Hannah Dela Cruz, Arindam Dutta +3
Human pose estimation is a critical tool across a variety of healthcare applications. Despite significant progress in pose estimation algorithms targeting adults, such developments…
SeGuE: Semantic Guided Exploration for Mobile Robots
Cody Simons, Aritra Samanta, Amit K. Roy-Chowdhury +1
The rise of embodied AI applications has enabled robots to perform complex tasks which require a sophisticated understanding of their environment. To enable successful robot operat…
Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes
Sarosij Bose, Arindam Dutta, Sayak Nag +4
Reconstructing 3D scenes from a single image is a fundamentally ill-posed task due to the severely under-constrained nature of the problem. Consequently, when the scene is rendered…
Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning
Udita Ghosh, Dripta S. Raychaudhuri, Jiachen Li +2
Preference-based reinforcement learning (RL) offers a promising approach for aligning policies with human intent but is often constrained by the high cost of human feedback. In thi…
Robust Offline Imitation Learning from Diverse Auxiliary Data
Udita Ghosh, Dripta S. Raychaudhuri, Jiachen Li +2
Offline imitation learning enables learning a policy solely from a set of expert demonstrations, without any environment interaction. To alleviate the issue of distribution shift a…
Language-guided Robust Navigation for Mobile Robots in Dynamically-changing Environments
Cody Simons, Zhichao Liu, Brandon Marcus +2
In this paper, we develop an embodied AI system for human-in-the-loop navigation with a wheeled mobile robot. We propose a direct yet effective method of monitoring the robot's cur…
Vision-based Xylem Wetness Classification in Stem Water Potential Determination
Pamodya Peiris, Aritra Samanta, Caio Mucchiani +3
Water is often overused in irrigation, making efficient management of it crucial. Precision Agriculture emphasizes tools like stem water potential (SWP) analysis for better plant s…