Cabin Suspension Sensing for Reliable Occupancy Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for detecting in-cabin occupancy in autonomous machines are often unreliable, as they may fail to accurately detect humans or other objects due to limitations in sensor fields of view, lighting conditions, and object recognition algorithms, leading to potential unsafe operating conditions when autonomous driving systems are engaged.
Innovation Solution
The use of suspension sensors to measure weight distribution within the cabin, combined with accelerometers and other sensors, to determine the presence of occupants by comparing measured values to reference patterns and thresholds, and adjusting for factors like speed and wind, with an AI algorithm processing sensor data to enhance detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional in-cabin perception sensors (cameras, LiDAR, RADAR) are used to detect occupant presence, then the system can identify objects within the cabin, but the detection reliability deteriorates due to limited sensor fields of view, lighting conditions, and false negatives/positives
Solution Approach 1:
The patent divides the detection task into multiple independent sensing channels: traditional perception sensors (cameras, LiDAR, RADAR) and suspension sensors (accelerometers, load cells). Each sensor type monitors different physical phenomena, and their results are combined to achieve more reliable detection. This segmentation allows the system to overcome the limitations of individual sensor types.
Solution Approach 2:
The suspension system, originally designed for mechanical support and vibration damping, is repurposed to perform occupant detection. The same suspension components that support the cabin structure are used to sense weight changes and acceleration patterns, enabling a single system to serve multiple functions: structural support, vibration isolation, and occupancy detection.
2Volume of moving object
If the cabin is designed to be relatively large to accommodate various functions, then the cabin can house necessary equipment and seating, but the sensor fields of view are blocked and detection accuracy deteriorates when occupants are in certain positions
Solution Approach 1:
The patent transitions from two-dimensional optical detection (camera fields of view) to three-dimensional gravitational field detection (suspension sensor network). The suspension sensors are distributed throughout the cabin structure at multiple locations, creating a volumetric detection capability that can sense occupants anywhere in the cabin space regardless of line-of-sight constraints.
3Reliability
If LiDAR sensors are used to overcome lighting condition limitations, then detection performance is less compromised by light, but the system cost increases and classification capability deteriorates
Solution Approach 1:
Instead of using expensive LiDAR sensors to replicate the functionality of expensive imaging systems, the patent uses inexpensive suspension sensors (accelerometers, load cells) that are already present in the vehicle for other purposes. These sensors copy the occupant detection function through a completely different physical mechanism (gravitational/acceleration sensing versus optical sensing), achieving similar reliability without the cost penalty.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This method provides a more reliable and accurate detection of in-cabin occupancy, preventing unsafe autonomous driving modes and ensuring safe operation by reliably identifying the presence of humans or objects within the cabin.
Implementation Method 1
determining, using one or more sensors, a value of a suspension characteristic of a suspension system of the autonomous machine; and determining whether an occupant is present in a cabin of the autonomous machine based at least on the value of the suspension characteristic
Implementation Method 2
measuring, using one or more accelerometers disposed on the cabin, a number of samples of an acceleration of the cabin over a period of time to generate an acceleration pattern during acceleration of the autonomous machine
Data Source
AI summary
Methods and systems to perform in-cabin occupancy detection in autonomous systems or applications are disclosed. Specifically, in many conventional trucks or other commercial vehicles, to improve a comfort level for drivers, a cabin of the vehicle can be connected to a chassis via a cabin suspension system, which may include damping springs. In some embodiments, sensors can be installed adjacent to or integrated with the damping springs of the cabin suspension system. Signals from the sensors can be used to detect a change in weight of the cabin compared to a baseline value, thereby detecting the presence of a person or other object in the cabin of the vehicle. A safety feature may be implemented in autonomous vehicles that prevents the operation of the vehicle in a fully autonomous driving mode when the cabin is occupied.