analiza aiqbench
This paper proposes a causal-inference framework for mobile robot navigation in crowds, where only the causal model's parameters are updated from a small set of real-world observations after simulation training. The reported gains over a non-causal baseline are promising, but they come from a single robot platform and limited scenarios, so generalization to other environments remains unproven. For AI and ML readers, the useful signal is the sim-to-real parameter-update approach, which keeps the causal structure fixed to reduce how much real-world data is needed.
A Practical Causal Framework for Autonomous Mobile Robots: From Simulation to Real-World Human Environments
arXiv:2611.04027v1 Announce Type: cross Abstract: Causal inference has emerged as a powerful paradigm enabling robots to make safe, efficient decisions by reasoning about the ``why'' behind events. However, its real-world application is hindered by the difficulty of collecting causal data, especially in human-populated environments where training takes time, while users expect immediate operation. To this end, we tackle the challenge of transferring simulation-learnt causal relations to the real world with minimal effort. While retaining the invariant high-level causal structure, we empirically demonstrate the system adapts efficiently to real-world situations by updating only the causal model parameters with a limited set of new observations. Our results show that the parameter update enables rapid sim-to-real transfer. The framework runs efficiently onboard of a mobile robot and significantly outperforms a non-causal baselines navigating successfully and safely in complex human-shared scenarios.
Abstract:Causal inference has emerged as a powerful paradigm enabling robots to make safe, efficient decisions by reasoning about the ``why'' behind events. However, its real-world application is hindered by the difficulty of collecting causal data, especially in human-populated environments where training takes time, while users expect immediate operation. To this end, we tackle the challenge of transferring simulation-learnt causal relations to the real world with minimal effort. While retaining the invariant high-level causal structure, we empirically demonstrate the system adapts efficiently to real-world situations by updating only the causal model parameters with a limited set of new observations. Our results show that the parameter update enables rapid sim-to-real transfer. The framework runs efficiently onboard of a mobile robot and significantly outperforms a non-causal baselines navigating successfully and safely in complex human-shared scenarios.
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2611.04027 [cs.RO]
(or arXiv:2611.04027v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2611.04027 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 228 cuvinte
Subiecte conexe
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
arXiv · 15 iun. 2026
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
arXiv · 12 iun. 2026
Real-time autonomous magnetic microrobot navigation across dynamic and biologically relevant environments
arXiv · 24 sept. 2026
Adaptive Memory Crystallization for Autonomous AI Agent Learning in Dynamic Environments
arXiv · 16 iun. 2026