Autonomous Vehicle Passenger Recognition via Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles lack an effective method to accurately recognize and support passenger boarding and alighting, particularly at stops, without a driver or guide, leading to potential safety and efficiency issues.
Innovation Solution
An apparatus and method that utilize a vehicle communicator, sensor, and controller to analyze images and information of people outside the vehicle, extract a passenger candidate group, calculate the number of reserved passengers, and adjust boarding standby time and stop positions based on passenger types, using a deep neural network model for route optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous vehicle operates without driver or guide, then automation level is improved, but passenger recognition and boarding support capability deteriorates
Solution Approach 1:
The patent introduces a passenger recognition system as an intermediary between the autonomous vehicle system and passengers. This system includes sensors (cameras, LIDAR) that detect passengers, a processor that analyzes sensor data to identify and count passengers, and a controller that manages boarding operations based on recognition results. This intermediary component enables the autonomous vehicle to reliably recognize and support passengers without human drivers or guides.
2Reliability
If passenger recognition system is added to autonomous vehicle, then boarding support capability is improved, but device complexity increases
Solution Approach 1:
The patent integrates the passenger recognition system with existing autonomous vehicle components. The processor that analyzes sensor data for passenger recognition is the same processor used for autonomous driving decisions. The sensors (cameras, LIDAR) serve dual purposes: capturing data for both passenger recognition and environmental mapping for navigation. This multi-functionality approach improves boarding support capability while minimizing additional system complexity.
3Measurement precision
If accurate passenger recognition is implemented, then boarding accuracy is improved, but processing time increases
Solution Approach 1:
The patent implements preliminary action by continuously capturing sensor data and performing preliminary analysis before the actual boarding process. The system pre-identifies potential passengers and prepares recognition results in advance, so when boarding is initiated, the processing is already substantially complete or can be quickly finalized. This reduces the time loss during actual boarding operations while maintaining high recognition accuracy.
Solution Approach 2:
The patent employs skipping by focusing computational resources on critical recognition tasks during boarding operations. The system identifies key features and makes rapid decisions about passenger presence and identity during the actual boarding window, skipping less critical analysis steps that can be performed later or in parallel. This rushing through of essential processing maintains accuracy while minimizing time loss.
Data Source
AI summary
Disclosed is an apparatus for passenger recognition and boarding/alighting support of an autonomous vehicle. An apparatus for passenger recognition and boarding/alighting support of an autonomous vehicle according to an embodiment of the present disclosure may include a vehicle communicator configured to receive scheduled passenger information, a sensor configured to sense people outside the vehicle, and a vehicle controller configured to extract a passenger candidate group by analyzing the sensed people outside the vehicle, and calculate the number of reserved passengers using the extracted passenger candidate group and the received scheduled passenger information. One or more of an autonomous vehicle, a server, and a terminal of the present disclosure may be associated or combined with an artificial intelligence module, a drone (Unmanned Aerial Vehicle, UAV), a robot, an AR (Augmented Reality) device, a VR (Virtual Reality) device, a device associated with 5G network services, etc.