Autonomous Vehicle Trajectory Planning with Contingency Homotopies

Solution Overview

Problem

Existing autonomous vehicle trajectory determination methods fail to account for unforeseen contingencies, leading to slower reactions when unexpected situations arise.

Innovation Solution

Implementing a system that considers both nominal and contingency homotopies to generate trajectories, decoupling their generation and performance, allowing the vehicle to proactively anticipate and respond to potential worst-case scenarios.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional trajectory determination methods are used, then the system is simpler to implement, but the reaction time to unforeseen contingencies is slower

Engineering Contradiction:

Improvereaction time to contingenciesVSAvoidtrajectory planning system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary action by pre-generating contingency homotopies and contingency trajectories in advance, before actual contingencies occur. The trajectory planning system proactively considers potential worst-case scenarios and prepares alternative trajectories ahead of time, enabling faster reaction when contingencies actually arise without needing to compute everything from scratch during the emergency situation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The trajectory planning system is segmented into distinct components: nominal homotopy generation, contingency homotopy generation, and trajectory optimization. By decoupling the generation of nominal and contingency homotopies, the system can independently prepare for different scenarios without interfering with each other, improving both reliability and computational efficiency.

Inventive Principle:

Principle #1Segmentation

2Reliability

If contingency homotopies are considered in trajectory planning, then the robustness of trajectory planning is enhanced, but the computational complexity increases

Engineering Contradiction:

Improverobustness of trajectory planningVSAvoidcomputational complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary action by pre-generating contingency homotopies and contingency trajectories in advance, before actual contingencies occur. The trajectory planning system proactively considers potential worst-case scenarios and prepares alternative trajectories ahead of time, enabling faster reaction when contingencies actually arise without needing to compute everything from scratch during the emergency situation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts between nominal and contingency trajectory generation based on the current situation. The trajectory planning system can switch between considering only nominal trajectories under normal conditions and incorporating contingency homotopies when risks are detected, making the computational complexity adaptive rather than static.

Inventive Principle:

Principle #15Dynamics

3Reliability

If the vehicle proactively anticipates contingencies, then the safety and human-like behavior are improved, but the processing time for nominal operation increases

Engineering Contradiction:

Improvesafety and human-like driving behaviorVSAvoidprocessing time for trajectory generation

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-generating contingency homotopies and contingency trajectories in advance, before actual contingencies occur. The trajectory planning system proactively considers potential worst-case scenarios and prepares alternative trajectories ahead of time, enabling faster reaction when contingencies actually arise without needing to compute everything from scratch during the emergency situation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies partial action by selectively generating contingency trajectories only when necessary, rather than always computing full contingency plans. The trajectory planning system can opt to generate only nominal trajectories under normal conditions and reserve contingency trajectory generation for situations where risks are detected, reducing unnecessary processing time while maintaining safety when needed.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12570328B2Autonomous vehicle with contingency consideration in trajectory realization

Publication Date: 2026.03.10 MOTIONAL AD LLC

AI summary

Provided are methods for determining a trajectory, which can include obtaining, using the at least one processor, sensor data associated with an environment in which a vehicle is operating, wherein the environment comprises one or more agents including a first agent; determining, using the at least one processor, based on the sensor data, a first prediction associated with the first agent; determining, using at least one processor, based on the first prediction, a primary homotopy; determining, using the at least one processor, based on the primary homotopy and the first prediction, one or more contingency homotopies associated with a contingency; determining, using the at least one processor, based on the primary homotopy and the one or more contingency homotopies, a primary trajectory; and providing, using the at least one processor, operation data associated with the primary trajectory to cause the vehicle to operate based on the primary trajectory.