Autonomous Vehicle Trajectory Validation With Heterogeneous Sensor Redundancy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing redundant systems in autonomous vehicles are not infallible, as faulty sensors or sensing schemes can result in unsafe and unreliable motion planning, despite the use of redundant motion planners.
Innovation Solution
The implementation of a heterogeneous redundancy check system in autonomous vehicles, where a main perception is formed using all sensors, and an auxiliary perception is formed using a subset of sensors to validate computed trajectories, reducing computational efforts while enhancing inconsistency detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If full redundant motion planners are run in parallel using all perception sensors, then reliability of motion planning is improved, but computational complexity and processing time increase significantly
Solution Approach 1:
The perception sensor set is segmented into two overlapping subsets: a first subset used by the first motion planner and a second subset used by the second motion planner. This segmentation allows each planner to operate with a manageable portion of sensors while maintaining overall system reliability through the overlap and cross-validation between the two planners.
2Measurement precision
If all perception sensors are used to form both main and auxiliary perceptions, then detection accuracy is improved, but computational resources required increase
Solution Approach 1:
The second motion planner uses only a second subset of perception sensors rather than all sensors, representing a partial action approach. This reduces the computational burden while still achieving sufficient detection accuracy for validation purposes, as the overlapping subsets ensure critical information is captured by both planners.
3Device complexity
If homogeneous sensor sets are used for both main and auxiliary perceptions, then system simplicity is maintained, but ability to detect inconsistencies is reduced
Solution Approach 1:
Different local qualities are assigned to the two sensor subsets used by the two motion planners. By configuring the subsets differently (overlapping but not identical compositions), the system creates local variations in sensor coverage that enable inconsistency detection while maintaining overall system functionality. This local differentiation enhances reliability without requiring complete homogeneity.
Data Source
AI summary
The invention is notably directed to an autonomous vehicle, e.g., an autonomous or semi-autonomous vehicle such as a self-driving car. The autonomous vehicle comprises a drive-by-wire (DbW) system (300), a set of perception sensors 21-24, such as lidars and cameras, and two processing systems, i.e., a first processing system (100) and a second processing system (200). The first processing system is configured to form a main perception based on signals from each of the perception sensors of the set, estimate states of the vehicle based on feedback signals from the DbW system, and compute trajectories for the autonomous vehicle based on the perception formed and the estimated states. The second processing system is configured to form an auxiliary perception based on signals from only a subset of the perception sensors, validate the computed trajectories based on the auxiliary perception formed, and cause to forward the validated trajectories to the DbW system. In other words, distinct perceptions are formed from overlapping sets of sensors, whereby one of the perceptions formed is used to validate trajectories obtained from the other. This requires less computational efforts, inasmuch as less signals (and therefore less information) are required to form the auxiliary perception. However, doing so is more likely to allow inconsistencies to be detected, thanks to the heterogeneity of sensor signals considered in input to the main and auxiliary perceptions. The invention is further directed to related methods and computer program products.