Topics
All robotics research topics
Ordered by how much share of monthly arXiv cs.RO each area has gained or lost over the last six months against the twelve before it. Every tag is a published keyword rule, not a model.
Vision-language-action
Policies that consume pixels and language and emit robot actions directly, usually fine-tuned from a VLM backbone.
World models
Learned simulators that predict future observations, so a policy can plan or train inside imagination instead of on hardware.
Tactile & force sensing
Touch as a first-class modality: skins, current sensing, and contact-rich feedback loops.
Foundation models & pretraining
Cross-embodiment pretraining, scaling laws, and the generalist-policy bet.
Simulation, sim-to-real & benchmarks
Simulators, domain randomisation, and the evaluation harnesses that decide whether a policy really works.
Humanoids & locomotion
Whole-body control, legged locomotion, and loco-manipulation on human-form robots.
Data collection & teleoperation
The unglamorous bottleneck: rigs, interfaces, and pipelines that produce robot demonstrations.
Egocentric & human data
Turning first-person human video and wearable capture into robot training signal, bypassing teleoperation.
Dexterous manipulation
Multi-fingered hands, in-hand reorientation, and contact-rich control of everyday objects.
Video & generative modeling
The upstream stack robotics borrows: video generation, diffusion and autoregressive models of pixels, and the representations they learn.
Safety & evaluation
Does it fail safely, and how would we know? Verification, red-teaming, and honest metrics.
Hardware & morphology co-design
Designing the body and the learning algorithm together instead of in sequence.
3D & spatial reasoning
Reconstruction, scene representation, and the geometry a policy needs to act in a room it has never seen.
Imitation & diffusion policies
Behaviour cloning at scale, and the generative-model action heads that made it work.
Human-robot interaction
Robots among people: social robots, collaboration, assistance, and the interfaces between human intent and robot action.
Navigation & mobility
Getting a body from A to B: mobile manipulation, exploration, and outdoor autonomy.
Reinforcement learning & control
Online and offline RL, model-predictive control, and the safety filters wrapped around them.
| Area | Papers here | With a kit | Share of cs.RO | Change |
|---|---|---|---|---|
| Vision-language-action | 339 | 4 | 11.89% | +7.1pp |
| World models | 295 | 12 | 7.61% | +2.86pp |
| Tactile & force sensing | 293 | 4 | 6.67% | +2.2pp |
| Foundation models & pretraining | 379 | 7 | 6.24% | +1.89pp |
| Simulation, sim-to-real & benchmarks | 377 | 4 | 5.9% | +1.58pp |
| Humanoids & locomotion | 381 | 6 | 5.9% | +1.31pp |
| Data collection & teleoperation | 448 | 10 | 6.76% | +0.91pp |
| Egocentric & human data | 330 | 14 | 4.62% | +0.86pp |
| Dexterous manipulation | 427 | 6 | 2.22% | +0.75pp |
| Video & generative modeling | 392 | 3 | 7.27% | +0.73pp |
| Safety & evaluation | 684 | 3 | 4.36% | +0.62pp |
| Hardware & morphology co-design | 194 | 2 | 3.59% | +0.48pp |
| 3D & spatial reasoning | 302 | 3 | 3.25% | -0.16pp |
| Imitation & diffusion policies | 280 | 6 | 6.24% | -0.32pp |
| Human-robot interaction | 112 | ยท | 4.53% | -0.4pp |
| Navigation & mobility | 636 | 3 | 19.33% | -0.84pp |
| Reinforcement learning & control | 579 | 10 | 15.4% | -1.43pp |
Papers here counts this site's corpus. Share of cs.RO is measured against every robotics submission that month. See Trends for the method.