Publications

Bi3: A Biplatform, Bicultural, Biperson Dataset for Social Robot Navigation

Andrew Stratton, Phani Teja Singamaneni, Pranav Goyal, Rachid Alami, Christoforos Mavrogiannis

IEEE International Conference on Robotics and Automation (ICRA) 2026

A dataset of close social robot navigation encounters between two humans and a robot, collected across two robot platforms and two sites (USA and France) with 74 participants. Bi3 provides 10.5 hours of multimodal human/robot motion tracks, RGB video, and u...

How Human Motion Prediction Quality Shapes Social Robot Navigation Performance in Constrained Spaces

Andrew Stratton, Phani Teja Singamaneni, Pranav Goyal, Rachid Alami, Christoforos Mavrogiannis

HRI 2026

We study how the accuracy of human motion prediction modules propagates through to downstream social navigation performance in tight, constrained spaces, where small prediction errors have outsized effects on planner behavior and human comfort.

Rethinking Legibility in Social Robot Navigation: Impact of Intent Representation and Human Attention

Pranav Goyal, Andrew Stratton, Christoforos Mavrogiannis

HRI 2026 Late Breaking Reports

Legible robot motion lets nearby people anticipate what a robot will do next, but most prior work on legibility assumes open spaces, static interactions, and fully attentive pedestrians. Through two hallway user studies with a Hello Robot Stretch 2, we show...

ACME: A Multi-Cultural, Multi-Embodiment Social-Navigation Dataset

Shashank Rao Marpally, Allan Wang, ... , Pranav Goyal, ... , Christoforos Mavrogiannis, Harold Soh

Under review, International Journal of Robotics Research (IJRR)

A large-scale social navigation dataset collected across 8 sites in 5 countries with 7 robot embodiments, comprising 29.35 hours of onboard robot data and 43.5 hours of overhead pedestrian tracking, built to capture how culture, geography, and embodiment sh...

SocRATES: Towards Automated Scenario-based Testing of Social Navigation Algorithms

Shashank Rao Marpally, Pranav Goyal, Harold Soh

IEEE Robotics and Automation Letters (RA-L)

SocRATES is an LLM-powered ROS2/Gazebo pipeline that automatically generates diverse, realistic test scenarios for social navigation algorithms and surfaces failure cases across varied human behaviors and contexts. Code: github.com/clear-nus/SocRATES.

Towards Automated Scenario Testing of Social Navigation Algorithims

Shashank Marpally, Pranav Goyal, Harold Soh

Unsolved Problems in Social Navigation workshop, RSS 2024

Use Google Scholar for full citation

LTLDoG: Satisfying Temporally-Extended Symbolic Constraints for Safe Diffusion-Based Planning

Zeyu Feng, Hao Luan, Pranav Goyal, Harold Soh

IEEE Robotics and Automation Letters

Use Google Scholar for full citation

Towards Automated Void Detection for Search and Rescue with 3D Perception

Ananya Bal, Pranav Goyal*, Ashutosh Gupta*, David Merrick, Robin Murphy, Howie Choset (* Equal contribution)

2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Use Google Scholar for full citation

A Comparison of Point Cloud Registration Techniques for on-site Disaster Data from the Surfside Structural Collapse

Ananya Bal, Robert Ladig, Pranav Goyal, John Galeotti, Howie Choset, David Merrick, Robin Murphy

2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)

Use Google Scholar for full citation

AI-based face recognition and skin pixel recognition for computer vision applications

Hindi Technical Seminar, CSIR - Structural Engineering Research Centre, Chennai, September 2021

The paper introduces a new threshold based skin and face detection method for extracting remote PPG signals for monitoring cardiac health. The propsed threshold values for skin pixels are tailored for the various skin tone found in Indian subcontinent regio...