A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI
arXiv:2505.01458v2 Announce Type: replace-cross Abstract: Navigation and manipulation are core capabilities in Embodied AI, but training agents to perform them directly in the real world is costly, time-consuming, and unsafe. Therefore, sim-to-real transfer has emerged as a key approach, yet the sim-to-real gap persists. This survey examines how physics simulators address this gap by analyzing properties that have received limited attention in prior surveys. We also analyze their features for navigation and manipulation tasks, as well as their hardware requirements. Additionally, we offer a re
The proliferation of embodied AI research necessitates advanced simulation tools for safe and efficient development, driving current efforts to bridge the 'sim-to-real' gap.
Improved physics simulators are critical for advancing robotics and embodied AI, enabling faster, safer, and more cost-effective development cycles for autonomous systems.
The focus for robotic development shifts further towards robust simulation environments that can accurately model real-world physics and hardware, reducing dependence on physical prototypes in early stages.
- · Embodied AI researchers
- · Robotics companies
- · Physics simulator developers
- · Hardware manufacturers
- · Companies relying solely on expensive real-world testing
- · Legacy simulation platforms
More sophisticated and capable embodied AI agents can be developed and deployed faster.
Reduced barriers to entry for robotics innovation as simulation costs decrease and effectiveness increases.
Accelerated commercialization and widespread adoption of general-purpose robots in diverse sectors.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI