Robotics Papers

Topics

The areas of robotics research, and which way each one is going

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.

AreaPapers hereWith a kitShare of cs.ROChange
Vision-language-action
Policies that consume pixels and language and emit robot actions directly, usually fine-tuned from a VLM backbone.
269 4 11.92% +7.1pp
World models
Learned simulators that predict future observations, so a policy can plan or train inside imagination instead of on hardware.
242 12 7.55% +2.85pp
Tactile & force sensing
Touch as a first-class modality: skins, current sensing, and contact-rich feedback loops.
262 4 6.69% +2.2pp
Foundation models & pretraining
Cross-embodiment pretraining, scaling laws, and the generalist-policy bet.
343 7 6.26% +1.9pp
Simulation, sim-to-real & benchmarks
Simulators, domain randomisation, and the evaluation harnesses that decide whether a policy really works.
317 4 6% +1.59pp
Humanoids & locomotion
Whole-body control, legged locomotion, and loco-manipulation on human-form robots.
320 6 5.92% +1.31pp
Data collection & teleoperation
The unglamorous bottleneck: rigs, interfaces, and pipelines that produce robot demonstrations.
392 10 6.78% +0.91pp
Egocentric & human data
Turning first-person human video and wearable capture into robot training signal, bypassing teleoperation.
295 14 4.55% +0.85pp
Dexterous manipulation
Multi-fingered hands, in-hand reorientation, and contact-rich control of everyday objects.
378 6 2.23% +0.75pp
Video & generative modeling
The upstream stack robotics borrows: video generation, diffusion and autoregressive models of pixels, and the representations they learn.
354 3 7.29% +0.73pp
Safety & evaluation
Does it fail safely, and how would we know? Verification, red-teaming, and honest metrics.
534 3 4.37% +0.63pp
Hardware & morphology co-design
Designing the body and the learning algorithm together instead of in sequence.
154 2 3.6% +0.48pp
3D & spatial reasoning
Reconstruction, scene representation, and the geometry a policy needs to act in a room it has never seen.
244 3 3.26% -0.16pp
Imitation & diffusion policies
Behaviour cloning at scale, and the generative-model action heads that made it work.
257 6 6.26% -0.32pp
Human-robot interaction
Robots among people: social robots, collaboration, assistance, and the interfaces between human intent and robot action.
91 ยท 4.55% -0.4pp
Navigation & mobility
Getting a body from A to B: mobile manipulation, exploration, and outdoor autonomy.
493 3 19.38% -0.83pp
Reinforcement learning & control
Online and offline RL, model-predictive control, and the safety filters wrapped around them.
507 10 15.35% -1.44pp

Papers here counts this site's corpus. Share of cs.RO is measured against every robotics submission that month. See Trends for the method.