This git collections articles on Accident prediction and avoidance. The goal of accident prediction tasks is different from the task of semantic segmentation, and motion planning of a single vehicle. Given that each vehicle has such methods in place, the larger scale problem is evaluating the risk in traffic/highway. One of the main sources of accidents are dash cam video data available on youtube. There has also been a recent effort in sharing this data freely across vehicles by anonymizing the driver/car.

Example of accident prediciton score from Dash cam videos (article below)

• Anticipating Accidents in Dashcam Videos link pdf
• Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization pdf
• ViewMap: Sharing Private In-Vehicle Dashcam Videos pdf
• Extracting Driving Behavior: Global Metric Localization from Dashcam Videos in the Wild pdf
• Probabilistic Driving Models and Lane Change Prediction pdf
• A Scenario-Adaptive Driving Behavior PredictionApproach to Urban Autonomous Driving pdf
• When will it change the lane? A probabilistic regression approach for rarely occurring events link
• Probabilistic Online POMDP Decision Making for Lane Changes in Fully Automated Driving link
• Probabilistic Lane Change Prediction in Highway Scenarios (master thesis) pdf
• Autonomous driving challenge: To Infer the property of a dynamic object based on its motion pattern using recurrent neural network pdf

• link
• A Non-Conservatively Defensive Strategy for Urban AutonomousDriving pdf