TRI-ML/RAP
This is the official code for the paper RAP: Risk-Aware Prediction for Robust Planning: https://arxiv.org/abs/2210.01368
This project helps self-driving vehicle engineers and researchers improve the safety and robustness of autonomous systems. It takes raw motion data from real-world driving scenarios or simulations and produces predictions of other agents' trajectories that are specifically biased towards risky, low-probability events. This allows planning algorithms to consider and react to potential dangers more effectively, helping autonomous vehicles make cautious decisions.
No commits in the last 6 months.
Use this if you need to train or evaluate a motion planning system that must account for rare but dangerous scenarios involving other vehicles or pedestrians, and you want your trajectory predictions to highlight these risks.
Not ideal if you are looking for general-purpose trajectory forecasting without a specific focus on risk awareness for autonomous planning, or if you need to deploy a commercial product without obtaining a commercial license.
Stars
46
Forks
8
Language
Python
License
—
Category
Last pushed
Sep 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TRI-ML/RAP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LucasAlegre/sumo-rl
Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with...
hilo-mpc/hilo-mpc
HILO-MPC is a Python toolbox for easy, flexible and fast development of...
reiniscimurs/DRL-robot-navigation
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin...
kyegomez/RoboCAT
Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation"...
OpenQuadruped/spot_mini_mini
Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion.