Autonomy Power Control Using Predicted Driving Conditions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in optimizing power consumption while maintaining safe navigation, as existing systems often consume excessive energy, affecting range and efficiency, especially in varying environmental conditions.

Innovation Solution

The autonomy system adjusts power consumption of sensors, compute cores, and actuators in real-time based on predicted environmental conditions, such as traffic density and weather, by modifying parameters like sensor data collection frequency, clock speed, and cooling systems, to optimize energy use without compromising safety.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the autonomy system operates all sensors and compute cores at full capacity continuously, then navigation safety and detection precision are maintained, but power consumption increases excessively

Engineering Contradiction:
Improvenavigation safetyVSAvoidpower consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The autonomy system dynamically adjusts the operational state of sensors and compute cores based on real-time environmental complexity assessment. When the environment is assessed as simple (e.g., clear weather, low traffic), the system transitions components to lower-power states or reduces their operational frequency, while maintaining full capacity in complex environments to ensure safety

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes operational parameters of autonomy components based on environmental conditions. This includes adjusting sensor sampling rates, compute core clock speeds, and cooling system frequencies according to the assessed complexity of the navigation environment, thereby optimizing power consumption while maintaining adequate performance

Inventive Principle:
Principle #35Parameter changes

2Use of energy by moving object

If the autonomy system reduces power consumption by lowering sensor and compute core activity, then energy efficiency improves, but detection precision and navigation safety may deteriorate

Engineering Contradiction:
Improveenergy efficiencyVSAvoiddetection precision
Core Design Contradiction:
Use of energy by moving objectVSMeasurement precision

Solution Approach 1:

The system adjusts operational parameters dynamically based on environmental complexity. In simple environments, parameters are reduced to improve energy efficiency, while in complex environments, parameters are increased to maintain detection precision and safety. This conditional parameter adjustment resolves the contradiction by adapting to situational requirements

Inventive Principle:
Principle #35Parameter changes

3Productivity

If the autonomy system operates at full power continuously, then system performance is maintained, but vehicle range is reduced

Engineering Contradiction:
Improvesystem performanceVSAvoidvehicle range
Core Design Contradiction:
ProductivityVSDuration of action of moving object

Solution Approach 1:

Instead of continuous full-power operation, the system employs periodic assessment of environmental complexity and adjusts power consumption accordingly. The autonomy system continuously monitors environmental conditions and modulates component operation between high-performance and energy-saving states, extending the duration of vehicle operation without sacrificing overall system performance

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The system dynamically transitions between different operational modes based on real-time environmental assessment, optimizing the balance between performance and energy consumption to maximize vehicle range while maintaining adequate performance levels

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4439123A1Methods and systems for modifying power consumption by an autonomy system
Publication Date: 2024.10.02 WAYMO LLC
  • EP4439123A1 patent drawingFigure 1
  • EP4439123A1 patent drawingFigure 2A
  • EP4439123A1 patent drawingFigure 2B

AI summary

Example embodiments relate to techniques for modifying power consumption of an autonomy system. For instance, a vehicle autonomy system may use sensor data from vehicle sensors to determine information about the surrounding environment and estimate one or more conditions expected for a threshold duration during subsequent navigation of the path by the vehicle. The autonomy system can then adjust operation of one or more of its components (sensors, compute cores, actuators) based on the one or more conditions expected for the threshold duration and power consumption data corresponding to the components. The vehicle can then be controlled based on subsequent sensor data obtained after adjusting operation of the components of the autonomy system thereby increasing the efficiency of the autonomy system in accordance with the vehicle's surrounding environment.