Robot Navigation Zone Setting Using People Flow Recognition States
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for setting entry prohibited areas for autonomous mobile robots require large amounts of walking data and often inaccurately designate passable areas, especially in low-density human environments, leading to potential entry into areas where people have mistakenly entered or where obstacles are undetectable by sensors.
Innovation Solution
An information processing apparatus that sets parameters for entry prohibited areas based on people flow data, utilizing velocity, acceleration, and jerk vectors to estimate a person's recognition state and update potential fields, thereby accurately defining passable and prohibited zones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If all areas are initially set as entry prohibited areas and potential is lowered for areas where people have existed, then entry prohibited areas can be automatically set, but a large amount of walking data is required to set a highly-reliable entry prohibited area
Solution Approach 1:
The patent applies preliminary action by pre-defining entry prohibited areas based on static environmental information (walls, obstacles, sensor detection zones) before robot operation begins. This preliminary setup eliminates the need to collect extensive walking data to identify prohibited areas, as they are established in advance using environmental maps and sensor configurations.
Solution Approach 2:
The system performs self-service by automatically generating entry prohibited areas from environmental data and sensor configurations without requiring manual marking or extensive data collection. The robot system itself generates the prohibited area definitions based on its sensor capabilities and environmental perception, eliminating the need for external data collection processes.
2Extent of automation
If all areas are initially set as entry prohibited areas and potential is lowered for areas where people have existed, then entry prohibited areas can be automatically set, but in a case where the distribution of people is low in density, only the vicinity of the center of the space tends to be treated as a passable area
Solution Approach 1:
The patent segments the space into distinct passable and prohibited areas based on environmental features rather than human presence patterns. By dividing the environment into zones defined by walls, obstacles, and sensor detection capabilities, the system accurately identifies passable areas regardless of low human density, avoiding the problem of only central areas being marked as passable.
Solution Approach 2:
The patent introduces environmental maps and sensor detection zones as intermediaries between human presence data and entry prohibited area definition. These intermediaries allow the system to accurately define prohibited areas based on environmental features and sensor capabilities rather than relying solely on human presence patterns, improving accuracy in low-density scenarios.
3Extent of automation
If all areas are initially set as entry prohibited areas and potential is lowered for areas where a person has existed, then entry prohibited areas can be automatically set, but an area where a person entered by mistake is set as a passable area
Solution Approach 1:
The patent applies preliminary anti-action by pre-establishing entry prohibited areas based on environmental features and sensor detection zones before robot operation begins. This prevents the robot from mistakenly entering prohibited areas in the first place, rather than relying on post-hoc analysis of human presence patterns that may include mistaken entries. The prohibited areas are defined in advance to prevent erroneous passable area designations.
Data Source
AI summary
The present technique relates to an information processing apparatus, an information processing method, and a program capable of easily setting a highly-reliable entry prohibited area. An information processing apparatus according to one aspect of the present technique sets a parameter of each area used for an action plan for a mobile object on the basis of a person's recognition state during movement estimated by people flow data. The present technique may be applied to an information processing apparatus that controls an autonomous mobile robot.