Autonomous Vehicle Time-Gap Planning at Intersections
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely navigating intersections with other road users, as existing spatial buffer methods may not adequately account for temporal proximity, potentially causing discomfort to passengers and other road users.
Innovation Solution
The method involves applying time gaps by adding temporal buffers to predicted future states of detected objects, allowing the autonomous vehicle to plan a trajectory that minimizes encroachment into these time gaps, thereby ensuring safe and socially acceptable navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If spatial buffer methods are used to maintain safe distances from other road users, then collision risk is reduced, but temporal proximity issues arise that may cause discomfort to passengers and other road users
Solution Approach 1:
The patent extends the traditional spatial buffer concept by adding a temporal dimension. Instead of only considering spatial distance thresholds, the system introduces time gap thresholds that evaluate both spatial and temporal proximity. This dimensional extension allows the vehicle to maintain appropriate spacing in both space and time, resolving the contradiction between collision avoidance and passenger comfort by ensuring that vehicles are not only spatially distant but also temporally separated from potential conflicts.
Solution Approach 2:
The system dynamically adjusts safety parameters by introducing time gap thresholds as an additional constraint alongside spatial distance thresholds. The planning system evaluates multiple parameters including spatial distance, time to collision, and temporal proximity to other road users. By changing the parameter set from purely spatial to spatio-temporal, the system achieves both collision avoidance and passenger comfort through more nuanced trajectory planning.
2Reliability
If distance thresholds are enforced to allow safe driving next to other road users, then safety is improved, but the autonomous vehicle may be slowed down or stopped excessively
Solution Approach 1:
The system employs dynamic threshold adjustment where distance and time gap thresholds are not fixed but adapt based on the operational context, vehicle speed, and surrounding traffic conditions. The planning system continuously evaluates whether enforced thresholds are appropriate for current conditions, allowing the vehicle to maintain higher speeds when safety margins are sufficient and reduce speed only when necessary to meet spatio-temporal separation requirements.
Solution Approach 2:
The patent changes the safety evaluation from static distance thresholds to dynamic spatio-temporal thresholds. The system considers multiple parameters including current speed, acceleration, time to intersection, and predicted trajectories of other road users. This parameter expansion allows the vehicle to optimize speed while maintaining safety by adjusting thresholds based on real-time conditions rather than applying fixed conservative limits.
3Reliability
If time gaps are applied to predicted future states of objects, then interactions with distant-but-close-in-time road users are avoided, but computational complexity increases
Solution Approach 1:
The system performs preliminary action by predicting future states of detected objects and pre-calculating time gaps before actual interactions occur. The planning system generates predicted trajectories for other road users and computes time gap thresholds in advance, allowing the autonomous vehicle to proactively plan trajectories that avoid future conflicts. This preliminary computation reduces real-time complexity by preparing safety margins before critical situations arise.
Solution Approach 2:
By adding the temporal dimension to safety planning, the system transforms collision avoidance from a reactive spatial problem to a proactive spatio-temporal problem. The planning system evaluates future states across both space and time dimensions, computing time gaps for predicted object positions. This dimensional extension, while increasing computational requirements, enables more efficient conflict resolution by identifying and avoiding potential interactions before they become immediate threats.
Data Source
AI summary
Aspects of the disclosure provide for a method of controlling an autonomous vehicle in an autonomous driving mode. For instance, a predicted future trajectory for an object detected in a driving environment of the autonomous vehicle may be received. A routing intent for a planned trajectory for the autonomous vehicle may be received. The predicted future trajectory and the routing intent intersect with one another may be determined. When the predicted future trajectory and the routing intent are determined to intersect with one another, a time gap may be applied to a predicted future state of the object defined in the predicted future trajectory. A planned trajectory may be determined for the autonomous vehicle based on the applied time gap. The autonomous vehicle may be controlled in the autonomous driving mode based on the planned trajectory.