Research map / Vision-language and multimodal / Human and embodied modeling
Harmonious Mobility for Robots that Work with and around People
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
A short research-summary paper outlining the author's work on harmonious robot mobility: passing-aware crowd navigation, user perception studies, and bystander-assisted field deployment.
Problem
Robots operating in unstructured, dynamic human spaces must model human behavior, understand user perceptions, and ensure safety and comfort during navigation and long-term deployment.
Approach
Formalizes pedestrian passing encounters mathematically using algebraic topology and builds a reactive, passing-aware model predictive controller for crowd navigation; also links quantitative robot behavior measures to user perceptions and leverages bystander help for lifelong deployment.
Key results
- Passing-aware MPC delivered significantly safer and more efficient performance than state-of-the-art baselines across lab experiments with diverse crowds (Mavrogiannis et al. 2023b).
- In a user study (N=105), the passing-aware controller yielded lower user acceleration and fewer reported robot disruptions than baselines.
- In a prior study, only 30 minutes of researcher help enabled a robot to navigate a 28,000 ft2 building floor for 4 days.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use passing-aware model predictive control instead of state-of-the-art baselines | robot crowd navigation · lab crowd experiments | safety | Helped |
| use passing-aware model predictive control instead of state-of-the-art baselines | robot crowd navigation · lab crowd experiments | efficiency | Helped |
| use passing-aware navigation instead of baselines | robot navigation in dense crowds · tight lab space | human acceleration | Helped |
| use passing-aware navigation instead of baselines | robot navigation in dense crowds · tight lab space | reported disruptions | Helped |
| provide 30’ of researcher help | robot navigation · 28,000 ft2 building floor | deployment duration: 4 days | Helped |
Limitations
- Paper is a short research statement; experimental details are deferred to cited works.
- Bystander help scalability is discussed as a challenge rather than solved.
Experimental setup
Metrics: safety efficiency acceleration user-reported disruptions
Baselines: state-of-the-art crowd navigation baselines
Builds on: model predictive control
Closest papers by meaning
- COOPERA: Continual Open-Ended Human-Robot Assistance (NeurIPS 2025 · similarity 0.79)
- Towards Autonomous Micromobility through Scalable Urban Simulation (CVPR 2025 · similarity 0.79)
- Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots (ICLR 2024 · similarity 0.78)
- Balancing Humans and Machines: A Study on Integration Scale and Its Impact on Collaborative Performance (AAAI 2024 · similarity 0.78)
- Homogeneous Dynamics Space for Heterogeneous Humans (CVPR 2025 · similarity 0.78)
- Back to the Future of Integrated Robot Systems (AAAI 2025 · similarity 0.78)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.