Autonomous Vehicle Sensor Redundancy for Social Interaction Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional autonomous vehicles are sub-optimally designed, inefficient in resource utilization, and poorly suited for managing inventory and rebalancing transportation services, with limitations in detecting and navigating social interactions, such as pedestrian and cyclist interactions, which poses safety risks.

Innovation Solution

A fleet of bidirectional autonomous vehicles equipped with advanced sensors and a communication platform that enables real-time trajectory calculations, teleoperation services, and efficient inventory management, allowing for safe and efficient navigation through sensor redundancy and adaptive lighting systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional autonomous vehicles are designed with a reserved driver seat and manual steering, then the vehicle can accommodate licensed drivers and provide safety backup, but the vehicle design becomes sub-optimal and resources are not conserved

Engineering Contradiction:
Improvesafety backupVSAvoidvehicle design
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent removes the driver seat, steering wheel, and manual control mechanisms from the vehicle design. By extracting these human-operated components, the vehicle achieves full automation without the complexity and resource consumption associated with accommodating human drivers, while maintaining safety through automated systems

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The vehicle is designed to perform all driving functions autonomously without human intervention. The automated steering, acceleration, and navigation systems enable the vehicle to serve itself, eliminating the need for driver seats and manual controls while optimizing resource utilization

Inventive Principle:
Principle #25Self-service

2Ease of operation

If conventional transportation services use privately-owned vehicles with human drivers, then passengers can access transportation services, but vehicle inventory is under-utilized and cannot be effectively rebalanced

Engineering Contradiction:
Improvetransportation service accessVSAvoidvehicle inventory utilization
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The autonomous vehicles are designed as part of a shared fleet that can be dynamically allocated to multiple users and locations. Each vehicle serves multiple purposes and multiple customers over time, maximizing inventory utilization. The fleet management system enables vehicles to transition between different service roles, achieving universal applicability across various transportation needs

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent implements a dynamic fleet management system that continuously repositions autonomous vehicles based on real-time demand patterns. Vehicles are automatically redirected to high-demand areas and rebalanced from low-utilization zones, enabling the inventory to adapt dynamically to changing transportation needs and maximize overall utilization

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If conventional approaches use LIDAR and camera sensors for object detection, then the vehicle can detect external objects, but the system is not sufficiently able to identify pedestrians, cyclists, and social interactions

Engineering Contradiction:
Improveobject detectionVSAvoidsocial interactions detection
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent combines multiple sensor types including LIDAR, cameras, and specialized interaction detection sensors into an integrated perception system. By merging these complementary sensing modalities, the system achieves both precise object detection and the ability to identify social interactions, pedestrians, and cyclists through data fusion that leverages the strengths of each sensor type

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system employs machine learning algorithms and neural networks as intermediaries that process raw sensor data and translate it into meaningful classifications of pedestrians, cyclists, and social interactions. These computational intermediaries bridge the gap between basic object detection and sophisticated interaction recognition, enabling the vehicle to understand complex social dynamics

Inventive Principle:
Principle #24Intermediary (Mediator)

4Ease of manufacture

If conventional driverless vehicles require manual steering and driver accommodation, then the vehicle can be based on existing automotive paradigms, but opportunities to simplify design and conserve resources are foregone

Engineering Contradiction:
Improvedesign based on conventional vehiclesVSAvoidresource consumption
Core Design Contradiction:
Ease of manufactureVSLoss of energy

Solution Approach 1:

The patent extracts and removes all components related to human driver accommodation including the driver seat, steering wheel, pedals, and associated safety systems. This extraction eliminates the energy and resources required to manufacture, maintain, and operate these unnecessary components, while the vehicle can still be manufactured using conventional automotive processes for the remaining automated systems

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS11022974B2Sensor-based object-detection optimization for autonomous vehicles
Publication Date: 2021.06.01 ZOOX INC
  • US11022974B2 patent drawing
  • US11022974B2 patent drawing
  • US11022974B2 patent drawing

AI summary

Various embodiments relate generally to autonomous vehicles and associated mechanical, electrical and electronic hardware, computer software and systems, and wired and wireless network communications to provide an autonomous vehicle fleet as a service. In particular, a method may include receiving an indication of a sensor anomaly, determining one or more sensor recovery strategies based on the sensor anomaly, and executing a course of action that ensures the autonomous vehicle system operates within accepted parameters. Alternative sensors may be relied upon to cover for the sensor anomaly, which may include a failed sensor while the autonomous vehicle is in operation.