Autonomous Robot Control Using Spatio-Temporal Environment Maps

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous behavior robots lack the ability to adapt their behavior to suit their surrounding environment effectively, as they do not have a comprehensive understanding of the spatial and temporal dynamics of the environment they operate in.

Innovation Solution

An information processing apparatus and method that utilizes a spatio-temporal map to store and update environment information, including data on people, objects, pets, and weather, allowing the robot to autonomously select behaviors based on this data and improve its interaction with users.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If autonomous behavior robots operate without comprehensive environment understanding, then device complexity is reduced, but adaptability to surrounding environment deteriorates

Engineering Contradiction:
Improveadaptability to surrounding environmentVSAvoidcomplexity of environment understanding system
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the environment understanding system into distinct modules: spatio-temporal map generation unit, behavior pattern recognition unit, and behavior selection unit. Each module processes specific aspects of environmental data independently, allowing the system to achieve comprehensive adaptability while maintaining manageable complexity through functional decomposition.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a temporal dimension to traditional spatial mapping by creating spatio-temporal maps that track environmental changes over time. This dimensional expansion enables the robot to understand not only where objects are but also how they move and change, significantly improving adaptability without proportionally increasing system complexity.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Adaptability or versatility

If the robot collects and processes comprehensive environment information, then behavior suitability for environment is improved, but loss of time for information processing increases

Engineering Contradiction:
Improvebehavior suitability for environmentVSAvoidtime for information processing
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent implements preliminary action by continuously updating and maintaining spatio-temporal maps in the background as environmental data becomes available. This allows the robot to have environment understanding prepared in advance, so when behavior decisions are needed, the information is already processed and ready for rapid selection, reducing real-time processing time.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system employs feedback mechanisms where the robot's past behaviors and their outcomes are recorded and used to refine future behavior selections. This feedback loop allows the robot to learn from experience, progressively improving behavior suitability while reducing the time needed for decision-making as patterns are recognized more efficiently over time.

Inventive Principle:
Principle #23Feedback

3Adaptability or versatility

If the robot uses simple behavior selection methods, then device complexity is reduced, but adaptability to different environments deteriorates

Engineering Contradiction:
Improveadaptability to different environmentsVSAvoidcomplexity of behavior selection system
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal behavior selection framework that can handle multiple types of environments and situations through a single integrated system. The spatio-temporal map and behavior pattern recognition units are designed to be environment-agnostic, capable of adapting to various settings (indoor, outdoor, structured, unstructured) without requiring separate specialized systems, thus achieving high adaptability with controlled complexity.

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

Data Source

PatentEP3789841B1Information processing device, information processing method, program, and autonomous robot control system
Publication Date: 2023.05.17 SONY GROUP CORP
  • EP3789841B1 patent drawingFigure 1
  • EP3789841B1 patent drawingFigure 2
  • EP3789841B1 patent drawingFigure 3

AI summary

[Object] To provide an information processing apparatus, an information processing method, a program, and an autonomous behavior robot control system that enable an autonomous behavior robot to perform a behavior more suitable for the surrounding environment. [Solving Means] An information processing apparatus includes a map generating unit and a behavior control signal generating unit. The map generating unit generates a spatio-temporal map on the basis of data obtained by a data obtaining unit of an autonomous behavior robot, the autonomous behavior robot including the data obtaining unit that obtains data related to surrounding environment information. The behavior control signal generating unit generates a behavior control signal for the autonomous behavior robot to move and obtain data from the data obtaining unit in order to obtain information to be added to the spatio-temporal map.