Pranav Goyal

Pranav Goyal

PhD Candidate in Robotics, University of Michigan

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

portfolio

publications

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

Published in 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 region. Our threshold values were able to give a SSIM score of 0.82 on SFA Dataset (Human skin image dataset).

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

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

Use Google Scholar for full citation

Recommended citation: Ananya Bal, Robert Ladig, Pranav Goyal, John Galeotti, Howie Choset, David Merrick, Robin Murphy, "A Comparison of Point Cloud Registration Techniques for on-site Disaster Data from the Surfside Structural Collapse." In the proceedings of 2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), 2022.

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

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

Use Google Scholar for full citation

Recommended citation: Ananya Bal, Ashutosh Gupta, Pranav Goyal, David Merrick, Robin Murphy, Howie Choset, "Towards Automated Void Detection for Search and Rescue with 3D Perception." In the proceedings of 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023.

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

Published in 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.

Recommended citation: Shashank Rao Marpally, Pranav Goyal, Harold Soh, "SocRATES: Towards Automated Scenario-based Testing of Social Navigation Algorithms." IEEE Robotics and Automation Letters (RA-L), 2026. https://arxiv.org/abs/2412.19595

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

Published in 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 shape appropriate social navigation behavior.

Recommended citation: Shashank Rao Marpally, ..., Pranav Goyal, ..., Christoforos Mavrogiannis, Harold Soh, "ACME: A Multi-Cultural, Multi-Embodiment Social-Navigation Dataset." Under review, International Journal of Robotics Research (IJRR), 2026. https://arxiv.org/abs/2607.21964

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

Published in 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 that legibility works best when a robot expresses its immediate interaction choice, e.g. which side it will pass on, rather than its final destination, and that this benefit holds up even when pedestrians are cognitively distracted.

Recommended citation: Pranav Goyal, Andrew Stratton, Christoforos Mavrogiannis, "Rethinking Legibility in Social Robot Navigation: Impact of Intent Representation and Human Attention." In the Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2026. https://chrismavrogiannis.com/pdfs/goyal2026rethinking.pdf

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

Published in 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.

Recommended citation: Andrew Stratton, Phani Teja Singamaneni, Pranav Goyal, Rachid Alami, Christoforos Mavrogiannis, "How Human Motion Prediction Quality Shapes Social Robot Navigation Performance in Constrained Spaces." In the proceedings of the ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2026. https://arxiv.org/pdf/2601.09856

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

Published in 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 user impressions, offering a benchmark for human motion prediction and robot control policies in densely occupied spaces. Code and data: github.com/fluentrobotics/bi3dataset.

Recommended citation: Andrew Stratton, Phani Teja Singamaneni, Pranav Goyal, Rachid Alami, Christoforos Mavrogiannis, "Bi3: A Biplatform, Bicultural, Biperson Dataset for Social Robot Navigation." In the proceedings of IEEE International Conference on Robotics and Automation (ICRA), 2026. https://arxiv.org/abs/2605.06863

talks

Mowito Robotics

Published:

Mowito Robotics is a robotics company, building robotics solutions for Warehouses. They focus on the software part of the solution and work on manipulators and mobile robots.

CLeaR Lab, NUS

Published:

CLeAR lab in National University of Singapore seeks to improve people’s lives through intelligent robotics. The central focus of the lab is on developing physical and social skills for robots.

Role: