← all repositories
ahundt/awesome-robotics

A robotics field guide that actually knows where the bodies are buried

A curated index of simulators, SLAM stacks, datasets, and the glue that holds robots together.

1.4k stars LearningDomain Apps
awesome-robotics
Velocity · 7d
+0.4
★ / day
Trend
steady
star history

What it does

This is a classic “awesome list” — a hand-maintained index of links, software libraries, papers, and datasets useful for building robots. Categories span simulators (CoppeliaSim, AirSim, Bullet), SLAM (Cartographer, ORB_SLAM2, ElasticFusion), machine learning frameworks, sensor drivers, calibration tools, and geometry libraries. Think of it as a map to the scattered archipelago of robotics tooling.

The interesting bit

The list is opinionated enough to be useful: it nods to related lists for coursework and computer vision, and it includes the author’s own research projects (the CoSTAR dataset, the “Good Robot” RL paper) with honest disclaimers. That transparency is rarer than it should be in curation.

Key highlights

  • Covers the full stack: simulators, kinematics solvers, point-cloud libraries, ROS tooling, and RL frameworks
  • Includes hard-to-find dataset collections (Dex-Net 2.0, Google Brain Robot Data, LabelFusion)
  • Explicitly links to competing awesome lists — a civic-minded rarity
  • Maintained by a robotics researcher, not a content farm

Caveats

  • No clear criteria for inclusion; some entries are just names with one-line descriptions
  • Heavy TensorFlow/Keras tilt in the ML section, with minimal PyTorch presence
  • Last substantial update timing is unclear from the README

Verdict

Worth bookmarking if you’re entering robotics or need a quick survey of established tools. Skip it if you want depth, benchmarks, or a living, automated index — this is a static field guide, not a search engine.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.