Autonomous Shuttle Situational Awareness for Dynamic Route Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Designing a system to autonomously drive shared or on-demand vehicles without human supervision at a level of safety required for practical acceptance and use is challenging, as it requires replicating the complex perception and reaction capabilities of human drivers.
Innovation Solution
Implementing a sensor suite with machine perception and computer vision, combined with a software suite for client applications and a controller that includes a deep learning accelerator, to enable situational awareness and autonomous navigation, allowing the vehicle to interact with passengers and navigate dynamic environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a sensor suite with machine perception and computer vision is implemented, then situational awareness capability is improved, but device complexity increases
Solution Approach 1:
The system divides the complex perception task into multiple specialized sensor components (cameras, LIDAR, radar, ultrasonic sensors) that each handle specific aspects of environmental sensing. This segmentation allows the system to achieve comprehensive situational awareness while managing complexity through modular architecture
Solution Approach 2:
The controller is designed to process data from multiple different sensor types and perform multiple functions including obstacle detection, navigation, passenger monitoring, and route optimization. This multi-functionality consolidates what would otherwise require separate systems into a single integrated unit, improving reliability without proportionally increasing complexity
2Extent of automation
If deep learning accelerators are integrated into the controller, then autonomous navigation capability is improved, but manufacturing complexity increases
Solution Approach 1:
The deep learning accelerator is integrated within the controller unit, creating a nested architecture where specialized processing components are embedded within the existing control system. This approach enables advanced autonomous navigation capabilities while avoiding the need for separate manufacturing processes for standalone accelerator units
Solution Approach 2:
The controller serves as an intermediary that manages the interface between the deep learning accelerator and the rest of the vehicle systems. This mediator role simplifies manufacturing by providing a standardized integration point that handles data flow and coordination, reducing the complexity burden on manufacturing processes
3Reliability
If multiple sensors monitor both external environment and passenger space, then safety and situational awareness are improved, but cost increases
Solution Approach 1:
The sensor suite is designed with multi-functional sensors that simultaneously perform external environmental monitoring and internal passenger space surveillance. For example, cameras positioned for external viewing also capture interior scenes, and the controller processes both external navigation data and internal passenger behavior data, thereby achieving enhanced safety without proportionally increasing the quantity of sensors required
Solution Approach 2:
The system merges the functionality of separate external and internal monitoring systems into a unified sensor suite and processing architecture. By combining sensor placements and data processing functions, the system achieves comprehensive safety monitoring while reducing the total component count and associated costs compared to having entirely separate monitoring systems
Data Source
AI summary
A system and method for an on-demand shuttle, bus, or taxi service able to operate on private and public roads provides situational awareness and confidence displays. The shuttle may include ISO 26262 Level 4 or Level 5 functionality and can vary the route dynamically on-demand, and/or follow a predefined route or virtual rail. The shuttle is able to stop at any predetermined station along the route. The system allows passengers to request rides and interact with the system via a variety of interfaces, including without limitation a mobile device, desktop computer, or kiosks. Each shuttle preferably includes an in-vehicle controller, which preferably is an AI Supercomputer designed and optimized for autonomous vehicle functionality, with computer vision, deep learning, and real time ray tracing accelerators. An AI Dispatcher performs AI simulations to optimize system performance according to operator-specified system parameters.