From Perception to Action: Representation-Centric Robot Autonomy

Overview

Representations connect perception, mapping, planning, and decision making across the autonomy stack. This workshop examines how geometric, probabilistic, dense, implicit, and learned representations shape the performance, scalability, and reliability of robotic systems, from sensing and localization to navigation, manipulation, and exploration.

Bringing together researchers across SLAM, perception, planning, learning, manipulation, and autonomous navigation, the workshop will compare task-dependent trade-offs among occupancy maps, signed distance fields, Gaussian splatting, neural fields, and other representations. Its goal is to clarify practical design choices, failure modes, and open problems for robust closed-loop autonomy while bridging classical model-based and modern data-driven approaches.

Keynote Speakers

Ayoung Kim

Associate Professor

Seoul National University

Teresa Vidal-Calleja

Professor

University of Technology Sydney

Maani Ghaffari

Assistant Professor

University of Michigan

Yixi Cai

Postdoctoral Fellow

KTH

Lantao Liu

Professor

Indiana University Bloomington

Guoquan (Paul) Huang

Professor

University of Delaware

Timothy D Barfoot

Professor

University of Toronto

John Leonard

Professor

MIT

Schedule

Time	Session	Speaker
8:30-8:35	Welcome & Introduction
8:35-9:00	Invited Talk 1 - From Geometry to Semantics: Toward Efficient Autonomous Navigation in the Wild	Lantao Liu Indiana University Bloomington
9:00-9:25	Invited Talk 2 - Visual-Inertial Perception: From Kinematics to Dynamics	Guoquan (Paul) Huang University of Delaware
9:30-9:55	Invited Talk 3 - Computational Symmetry and Learning for Robotics	Maani Ghaffari University of Michigan
9:55-10:20	Invited Talk 4 - Local Maps Are All You Need	Timothy D Barfoot University of Toronto
10:20-10:50	Poster Session & Coffee Break
10:50-11:15	Invited Talk 5 - Continuous Safety: Spatial Fields for Control, Planning, and Learning	Teresa Vidal-Calleja University of Technology Sydney
11:15-11:30	Early Career Talk - An Efficiency-Centric View of Map Representations for Robotics	Yixi Cai KTH Royal Institute of Technology
11:35-12:00	Invited Talk 6 - From Geometry to Neural Fields: Representation Choices for Robust and Scalable LIDAR Autonomy	Ayoung Kim Seoul National University
12:00-12:25	Invited Talk 7 - Towards "Undo" for the Physical World	John Leonard MIT
12:25-12:30	Closing Remarks