2 citations · 4 across the 10 of their papers we have counts for
10 papers
VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision
Gershom Seneviratne, Yohan Abeysinghe, Jianyu An +3
We introduce VEGA, an approach for training navigation VisionLanguage-Action (VLA) models from unlabeled egocentric navigation videos. Internet-scale egocentric videos provide a sc…
CHOP: Counterfactual Human Preference Labels Improve Obstacle Avoidance in Visuomotor Navigation Policies
Gershom Seneviratne, Jianyu An, Vaibhav Shende +6
Visuomotor navigation policies have shown strong perception-action coupling for embodied agents, yet they often struggle with safe navigation and dynamic obstacle avoidance in comp…
PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation
Samarth Chopra, Jing Liang, Gershom Seneviratne +1
Understanding physical properties such as friction, stiffness, hardness, and material composition is essential for enabling robots to interact safely and effectively with their sur…
DR. Nav: Semantic-Geometric Representations for Proactive Dead-End Recovery and Navigation
Vignesh Rajagopal, Kasun Weerakoon Kulathun Mudiyanselage, Gershom Devake Seneviratne +5
We present DR. Nav (Dead-End Recovery-aware Navigation), a novel approach to autonomous navigation in scenarios where dead-end detection and recovery are critical, particularly in…
Splatblox: Traversability-Aware Gaussian Splatting for Outdoor Robot Navigation
Samarth Chopra, Jing Liang, Gershom Seneviratne +5
We present Splatblox, a real-time system for autonomous navigation in outdoor environments with dense vegetation, irregular obstacles, and complex terrain. Our method fuses segment…
HALO: Human Preference Aligned Offline Reward Learning for Robot Navigation
Gershom Seneviratne, Jianyu An, Sahire Ellahy +5
In this paper, we introduce HALO, a novel Offline Reward Learning algorithm that quantifies human intuition in navigation into a vision-based reward function for robot navigation.…
ViLAM: Distilling Vision-Language Reasoning into Attention Maps for Social Robot Navigation
Mohamed Elnoor, Kasun Weerakoon, Gershom Seneviratne +3
We introduce ViLAM, a novel method for distilling vision-language reasoning from large Vision-Language Models (VLMs) into spatial attention maps for socially compliant robot naviga…
BehAV: Behavioral Rule Guided Autonomy Using VLMs for Robot Navigation in Outdoor Scenes
Kasun Weerakoon, Mohamed Elnoor, Gershom Seneviratne +5
We present BehAV, a novel approach for autonomous robot navigation in outdoor scenes guided by human instructions and leveraging Vision Language Models (VLMs). Our method interpret…
Robot Navigation Using Physically Grounded Vision-Language Models in Outdoor Environments
Mohamed Elnoor, Kasun Weerakoon, Gershom Seneviratne +5
We present a novel autonomous robot navigation algorithm for outdoor environments that is capable of handling diverse terrain traversability conditions. Our approach, VLM-GroNav, u…
CROSS-GAiT: Cross-Attention-Based Multimodal Representation Fusion for Parametric Gait Adaptation in Complex Terrains
Gershom Seneviratne, Kasun Weerakoon, Mohamed Elnoor +5
We present CROSS-GAiT, a novel algorithm for quadruped robots that uses Cross Attention to fuse terrain representations derived from visual and time-series inputs; including linear…