Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior



Supplementary Material
CVPR 2022


Results

planner and adversary shown in each example



Collision Scenario Clusters (Sec 5.2)
Generated collision scenarios are clustered and labeled based on the relative position and heading of the adversary and planner at the time of collision. Representative examples from each of these clusters is shown below.

T-Bone Right
Merge Right
Head On
Front Right
Cutoff Right
Behind
T-Bone Left
Merge Left
Front Left
Cutoff Left & Front

Adversarial Optimization for Replay Planner:
STRIVE (ours) vs. Bicycle Baseline (Sec 5.1)
Qualitative examples of scenarios generated by STRIVE compared to the Bicycle baseline which does not use the learned traffic model in any way. In each example, the original scene used for initialization is shown on the left followed by the output of Bicycle adversarial optimization and ours. Note the unrealistic attacks containing sharp turns from Bicycle.

Original replay
Bicycle attack
STRIVE attack
The adversary turns sharply to block the planner in a seemingly malicious fashion.
The adversary suddenly changes lanes in a more realistic way, since STRIVE uses the learned prior.
Original replay
Bicycle attack
STRIVE attack
Original replay
Bicycle attack
STRIVE attack
The adversary unnecessarily loops around to collide, since only its dynamics are regularized in optimization.
The adversary instead slows down to cause a rear-end collision, which is more likely under the prior.
Original replay
Bicycle attack
STRIVE attack

STRIVE Scenario Generation for Rule-based Planner (Sec 5.1)
From an initial nuScenes scenario (left) STRIVE uses an adversarial optimization to attack a given planner (middle). Furthermore, a solution optimization (right) ensures the generated scenario is "solvable" and thus useful for downstream tasks.

Original replay
STRIVE attack
STRIVE solution
Original replay
STRIVE attack
STRIVE solution
Original replay
STRIVE attack
STRIVE solution
Original replay
STRIVE attack
STRIVE solution

Second-order Effects (Supplementary Sec 4.4)
Here we show examples of scenarios where the Rule-based planner collision is caused through some sort of "second-order effect", i.e. multiple adversaries act in conjunction to cause a collision in some way. In all these examples, the planner is obstructed by one adversary, causing the planner to slam on its brakes and get hit by a different vehicle.

Original replay
STRIVE attack
Original replay
STRIVE attack
Original replay
STRIVE attack
Original replay
STRIVE attack

Pedestrian and Cyclist Adversaries (Supplementary Sec 4.7)
We train our traffic model on all categories in the nuScenes dataset and use it to generate scenarios for the Replay planner. In the examples below, a specific pedestrian or cyclist adversary is chosen before optimization to cause the collision.

Pedestrian adversary
Pedestrian adversary
Cyclist adversary
Cyclist adversary