Durant35/stanford_self_driving_car_learning

Stanford Code From Cars That Entered DARPA Grand Challenges

C++

Stanford Self Driving Car Learning

Stanford Code From Cars That Entered DARPA Grand Challenges.

Software Infrastructure for Stanford's Autonomous Vehicles.

See http://robots.stanford.edu/papers/junior08.pdf.

Originally found on Sourceforge.

Perception Guides

David Held, works in 2013~2016

In developing fast, effective algorithms for model-free segmentation and tracking.
- 3D Segmentation: A Probabilistic Framework for Real-time 3D Segmentation using Spatial, Temporal, and Semantic Cues
- Tracking: Combining 3D Shape, Color, and Motion for Robust Velocity Estimation
  - Github: precision-tracking
Alex Teichman, works in 2011~2013

Multiclass track classification, where model-free segmentation and tracking is at least somewhat reliable.
- Fully-supervised Track Classifier
  
  Teichman A, Levinson J, Thrun S. Towards 3D object recognition via classification of arbitrary object tracks[C]//Robotics and Automation (ICRA), 2011 IEEE International Conference on. IEEE, 2011: 4034-4041.
- Semi-supervised: Offline
  
  Teichman, Alex, and Sebastian Thrun. Tracking-based semi-supervised learning, Robotics: Science and Systems (RSS), 2011.
  
  Teichman, Alex, and Sebastian Thrun. "Tracking-based semi-supervised learning." The International Journal of Robotics Research 31.7 (2012): 804-818.
- Semi-supervised: Online
  
  Teichman, Alex, and Sebastian Thrun. "Group induction." Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on. IEEE, 2013.