Machine Controller for Joint Sensing and Motion in Uncertain Environments

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Autonomous machines operating in partially unknown environments face challenges in balancing information acquisition through sensing with the need to achieve control objectives, as excessive sensing can lead to cautious motion and performance degradation, while inadequate sensing may result in unsafe events.

Innovation Solution

A controller that employs interdependent but imbalanced control and sensing applications, where control is the primary objective and sensing is secondary, using multivariable constrained optimization to determine state trajectories and knowledge requirements, with probabilistic constraints accounting for uncertainty and safety margins.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the machine operates to acquire more information on the environment through sensing, then the knowledge of the object state becomes more precise, but the machine may deviate significantly from the path needed to achieve the control goal resulting in performance degradation

Engineering Contradiction:

Improveknowledge of object stateVSAvoidperformance in achieving control goal

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent applies partial action by selectively sensing only those environmental aspects that are critical for safe operation and goal achievement. Rather than continuously acquiring maximum information, the system performs sensing actions only when and where needed, balancing information acquisition with progress toward the control goal.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The sensing strategy is made dynamic by continuously adapting the sensing plan based on current knowledge, uncertainty levels, and proximity to the control goal. The system transitions between different sensing intensities and priorities as the machine's understanding of the environment evolves during operation.

Inventive Principle:

Principle #15Dynamics

2Loss of information

If the machine operates to acquire more information on the environment, then the amount of information acquired increases, but the machine may move too close to obstacles before enough knowledge is available presenting safety risks

Engineering Contradiction:

Improveinformation acquisitionVSAvoidsafety

Core Design Contradiction:

Loss of informationVSReliability

Solution Approach 1:

The system performs preliminary sensing actions before approaching potential obstacles or uncertain regions. By proactively gathering information about the environment in advance, the machine reduces uncertainty before critical decisions must be made, ensuring safer operation without sacrificing information acquisition.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system continuously updates its knowledge of the environment based on sensor feedback and uses this information to adjust its trajectory and sensing priorities. This closed-loop approach ensures that information acquisition is directly tied to reducing uncertainty in ways that improve safety and goal achievement.

Inventive Principle:

Principle #23Feedback

3Reliability

If the motion of the machine is determined solely based on available knowledge to avoid unsafe events, then safety is improved, but the motion becomes overly cautious resulting in degraded performance such as longer time to reach goal and more energy used

Engineering Contradiction:

ImprovesafetyVSAvoidenergy consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system applies partial sensing action by focusing computational and sensing resources only on the most critical uncertainties that affect safety and goal achievement. Rather than conservatively accounting for all possible uncertainties, the system identifies and addresses only those that have significant impact, reducing unnecessary caution and energy consumption.

Inventive Principle:

Principle #16Partial or excessive action

4Measurement precision

If the machine operates closer to obstacles to acquire more information, then the amount of information acquired increases, but the risk of collision increases

Engineering Contradiction:

Improveinformation on object stateVSAvoidcollision risk

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary sensing from safer distances before approaching obstacles. By gathering initial information about obstacle locations and characteristics in advance, the machine can plan more informed approaches that reduce collision risk while still acquiring necessary information for precise operation.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11886196B2Controlling machine operating in uncertain environment discoverable by sensing

Publication Date: 2024.01.30 MITSUBISHI ELECTRIC RESEARCH LABORATORIES INC

AI summary

A controller of a machine determines jointly a sequence of control inputs defining a state trajectory of the machine and a desired knowledge of the environment by solving a multivariable constrained optimization of a model of dynamics of the machine relating the state trajectory with the sequence of control inputs subject to a constraint on admissible values of the states and the control inputs defined based on the desired knowledge of the surrounding environment represented by the state of the environment and the uncertainty of the state of the environment determined from the measurements of the environment. In such a manner, the controller performs joint but imbalance optimization of the control inputs and the sensing instructions to the sensor for learning the environment.