Distributed Sensor Fusion for X-by-Wire Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for sensor fusion and autonomous control are often point solutions that rely on specific sensors and actuators, requiring significant changes if they are altered, and are typically retrofitted to mimic human input, limiting the number of control signals and becoming a serious limitation as the number of sensors and actuators grow in advanced autonomous vehicles.
Innovation Solution
A scalable sensor fusion system with autonomous x-by-wire control that uses a distributed processing cloud environment with virtualization, allowing for horizontal scalability and fault-tolerance, eliminating mechanical linkages between sensors and actuators, and providing a sensor-agnostic platform for sensor fusion, enabling full x-by-wire control without traditional mechanical means.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional sensor fusion systems are retrofitted to mimic human input, then the system can be integrated with existing mechanical control structures, but the number of control signals is limited and the system becomes a serious limitation as the number of sensors and actuators grow
Solution Approach 1:
The patent replaces mechanical linkages and human-mimicry control structures with a fully digital x-by-wire control system. Sensors connect directly to processing nodes that communicate with actuators through standardized digital interfaces, eliminating the need for mechanical linkages and human input simulation. This substitution enables unlimited control signals to be transmitted electronically without the physical constraints of mechanical systems.
Solution Approach 2:
The patent implements a universal processing node architecture that can handle any sensor type and actuator type through standardized interfaces. The processing nodes are designed to be sensor-agnostic and actuator-agnostic, capable of processing data from multiple sensor modalities (LIDAR, cameras, radar, etc.) and controlling various actuators (steering, braking, acceleration, etc.) through a unified digital communication protocol, thereby achieving multi-functionality and adaptability.
2Reliability
If processing nodes are distributed and connected in a network, then the system achieves horizontal scalability and fault-tolerance, but the device complexity increases
Solution Approach 1:
The patent divides the autonomous vehicle's processing system into multiple independent processing nodes distributed throughout the vehicle. Each processing node is a self-contained unit with its own sensors, computation resources, and actuators it can control. This segmentation allows the system to scale horizontally by adding more nodes and provides fault-tolerance because each node operates independently - if one node fails, others continue to function and can take over its responsibilities.
Solution Approach 2:
The patent introduces a standardized communication protocol and message bus as an intermediary layer between processing nodes, sensors, and actuators. This intermediary abstracts the complexity of inter-node communication, allowing nodes to exchange information through standardized messages without needing complex point-to-point connections. The message bus handles routing, synchronization, and error handling, thereby reducing the apparent complexity for individual nodes while enabling robust distributed operation.
3Weight of moving object
If mechanical linkages are eliminated in favor of direct digital control, then weight is reduced and scalability is improved, but the system requires advanced computer control infrastructure
Solution Approach 1:
The patent eliminates mechanical linkages between sensors and actuators entirely, replacing them with direct digital communication through processing nodes. Sensors connect to processing nodes via electrical connections, and processing nodes send control commands to actuators through the same digital infrastructure. This substitution removes the weight of mechanical linkages (shafts, gears, linkages) while enabling flexible, reconfigurable control architectures that can be updated through software rather than physical reconfiguration.
Data Source
AI summary
An autonomous system for x-by-wire control includes processing nodes distributed and connected to one another. Sensors are connected to the processing nodes. Actuators are configured to directly control the autonomous system driven by and connected to the processing nodes for x-by-wire control. The processing nodes are configured to: partition and map processing tasks between the processing nodes, and merge and reduce results of individual processing tasks into an actionable table that specifies objectives for the autonomous system.


