Mandatory Performance Requirements
The system will…
M.P.1 Collect 10 km of synthetic sensor data and ground truth from the simulator.
M.P.2 Detect oncoming vehicles in simulator up to a distance of 100 m in with a mAP of 0.4.
M.P.3 Detect lane markings with an accuracy of 75% within a maximum offset of 0.5 m.
M.P.4 Predict oncoming vehicle’s trajectory 2 second into the future with an RMSE of less than 3 m with respect to the ground truth trajectory.
M.P.5 Predict ego-trajectory 3 seconds into the future with an RMSE of less than 2 meters with respect to the ground truth trajectory.
M.P.6 Perform tracking and fusion with MOTA (multi-object tracking accuracy) of 60% and MOTP (multi-object tracking precision) of 55%.
M.P.7 Visualize detections with track IDs, occupancy grids with objects and road lanes, and future trajectories of oncoming vehicles at a minimum of 5 FPS.
M.P.8 Perform perception and prediction in real-time at 10 FPS.
M.P.9 Predict the possibility of a head-on collision (small overlap) in simulator with an accuracy of 80% also in 90% of the cases we should not detect the false positives.
M.P.10 Plan an optimal and feasible evasive maneuver trajectory for the ego-vehicle within 50ms.
M.P.11 Ego-vehicle tracks the optimal trajectory with an error of less than 1m in Carla.
M.P.12 Ego-vehicle camera detects the position of the other RC car within a tolerance of ±50cm of the ground truth position.
M.P.13 Detect the oncoming RC car using sensor fusion within a position tolerance of ±30cm.
M.P.14 Detect the oncoming RC car velocity using sensor fusion within a tolerance of 15% of the ground truth RC car velocity.
Mandatory Non-Functional Requirements
The system shall…
M.N.1 Collect data (at 30 FPS for Point Grey) within a maximum drop rate of 10% and visualize in Rviz
M.N.2 Warn driver in case of system failure
M.N.3 Be economically justifiable to develop the system
Desired Performance Requirements
The system will…
D.P.1 Detect roadside obstacles with an accuracy mAP of 0.3
D.P.2 Detect terrain with an accuracy (IoU) of 70%
D.P.3 Meet detection requirements on roads up to 10° incline/decline
D.P.4 Meet detection requirements on curved roads having a radius of curvature of up to 250 m
D.P.5 Predict the possibility of side-swipes with an accuracy of 60%
D.P.6 Meet detection and prediction requirements at speeds of up to 65 mph in the simulator
Desired Non-Functional Requirements
The system shall…
D.N.1 Use a secondary RC Car as an on-coming vehicle during demonstration
D.N.2 Meet detection and prediction requirements in low-light conditions
D.N.3 Meet detection and prediction requirements in weather conditions like light snow and rain
D.N.4 Notify police and emergency services in the event of a crash
D.N.5 Have a modular software architecture for easy integration of different sensors
D.N.6 Log potential crash data for continuous system improvements