Autonomous Pickup Maneuver Learning for Obstruction Handling

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in handling exceptional situations, such as obstructions, where they cannot assess or understand the intentions of other road users, leading to inefficiencies and potential safety issues, as they require human intervention for assistance.

Innovation Solution

A system and method that enables autonomous vehicles to classify obstruction situations, assess risks, and autonomously navigate around them or request tele-operator assistance, optimizing parameter values for pickup/drop-off maneuvers using customer and tele-operator feedback, and reducing the need for human intervention by generating optimized parameter values for execution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If autonomous vehicles use fixed parameter values for pickup/drop-off maneuvers, then the system is simple to operate, but it cannot adapt to exceptional situations such as obstructions

Engineering Contradiction:
Improveadaptability to exceptional situationsVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system dynamically adjusts pickup/drop-off parameters based on real-time environmental conditions and feedback. Instead of using fixed parameter values, the AV modifies parameters like stopping position, door opening angle, and passenger assistance actions according to detected obstructions and situation characteristics, enabling adaptability without requiring complete system redesign

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system implements feedback loops where customer responses and tele-operator inputs are continuously incorporated to refine parameter selection. This feedback mechanism allows the AV to learn from exceptional situations and improve its parameter adjustment strategies over time, balancing adaptability with systematic learning rather than random complexity

Inventive Principle:
Principle #23Feedback

2Reliability

If autonomous vehicles require tele-operator assistance for all exceptional situations, then safety is maintained, but operational time and costs increase

Engineering Contradiction:
ImprovesafetyVSAvoidoperational time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system applies tele-operator assistance partially - only when exceptional situations exceed the AV's autonomous处理能力. For common obstructions and routine adjustments, the AV handles matters independently using its parameter adjustment capabilities. Tele-operators intervene only for complex or uncertain situations, reducing overall intervention time while maintaining safety for critical cases

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The AV serves itself by autonomously detecting exceptional situations, assessing their severity, and adjusting parameters without immediate human intervention. The system independently handles routine exceptional situations through its sensing and decision-making capabilities, reserving tele-operator resources for cases requiring human judgment, thus reducing operational delays

Inventive Principle:
Principle #25Self-service

3Manufacturing precision

If autonomous vehicles collect and process customer and tele-operator feedback, then parameter optimization improves, but data processing complexity increases

Engineering Contradiction:
Improveparameter optimization precisionVSAvoiddata processing complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The feedback processing system is segmented into distinct functional modules: data collection from customers and tele-operators, feedback validation, parameter analysis, and optimization execution. Each module handles specific aspects of feedback processing independently, reducing overall system complexity while enabling comprehensive parameter optimization through coordinated module operation

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS11181927B2Automated learning system for improved pickup/dropoff maneuver
Publication Date: 2021.11.23 RENAULT SA
  • US11181927B2 patent drawing
  • US11181927B2 patent drawing
  • US11181927B2 patent drawing

AI summary

A method for performing a pickup/drop-off at a location includes providing, to an autonomous vehicle (AV), a parameter value of a parameter associated with the pickup/drop-off. The AV executes the pickup/drop-off according to the parameter value. After the pickup/drop-off is executed, feedback related to the parameter is received from a customer and from a tele-operator. The method also includes identifying other world objects present at the location during the pickup/drop-off and generating an optimized parameter value for executing the pickup/drop-off using the parameter value, the customer feedback, the tele-operator feedback, and other world objects.