Robot Intelligence Kernel for Dynamic Autonomous Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robot architectures lack a scalable framework for dynamic autonomy and generic robot attributes, making it difficult to port behaviors across different robot platforms and applications, resulting in limited autonomous decision-making capabilities and reliance on human operators for navigation.
Innovation Solution
A robot intelligence kernel with a generic scalable architecture that provides dynamic autonomy, allowing for autonomous navigation by defining an event horizon, detecting obstacles, and adjusting velocities based on proximity, enabling seamless portability across various robot platforms and interaction levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a generic scalable robot architecture is implemented, then portability across robot platforms is improved, but device complexity increases
Solution Approach 1:
The robot architecture is divided into distinct layers: hardware abstraction layer, robot attribute layer, and behavior layer. This segmentation allows each layer to be developed and ported independently, reducing the complexity of cross-platform adaptation while maintaining overall system coherence.
Solution Approach 2:
The patent implements universal robot attributes and behaviors that can function across multiple robot platforms. Generic attributes such as position, velocity, and orientation are defined in a platform-independent manner, enabling the same behavior code to operate on different hardware configurations without modification.
2Extent of automation
If dynamic autonomy framework is implemented, then autonomous decision-making capability is improved, but device complexity increases
Solution Approach 1:
The autonomy framework implements dynamic behavior adjustment where robots can transition between different autonomy levels based on situational requirements. The system dynamically selects appropriate behavior strategies (reactive, deliberative, or collaborative) rather than using a fixed complex control structure, reducing overall system complexity while maintaining high autonomous capability when needed.
Solution Approach 2:
The patent implements partial autonomy where specific navigation and obstacle avoidance functions operate autonomously while other functions remain under human control. This partial action approach provides sufficient autonomous decision-making for critical functions without requiring full system automation, thereby reducing complexity.
3Reliability
If event horizon-based obstacle detection is implemented, then navigation safety is improved, but computational requirements increase
Solution Approach 1:
The event horizon concept implements partial detection by focusing computational resources only on obstacles within a dynamically calculated safety distance (event horizon). Obstacles beyond this horizon are not fully processed, reducing computational energy consumption while maintaining navigation safety for relevant threats.
Solution Approach 2:
The event horizon distance parameter is dynamically adjusted based on robot velocity and environmental conditions. When moving at high speed, the event horizon expands to provide earlier warning, while at low speeds it contracts to reduce computational load. This parameter adaptation maintains safety reliability while optimizing energy consumption across different operational states.
Data Source
AI summary
A robot platform includes perceptors, locomotors, and a system controller, which executes instructions for autonomously navigating a robot. The instructions repeat, on each iteration through an event timing loop, the acts of defining an event horizon based on the robot's current velocity, detecting a range to obstacles around the robot, testing for an event horizon intrusion by determining if any range to the obstacles is within the event horizon, and adjusting rotational and translational velocity of the robot accordingly. If the event horizon intrusion occurs, rotational velocity is modified by a proportion of the current rotational velocity reduced by a proportion of the range to the nearest obstacle and translational velocity is modified by a proportion of the range to the nearest obstacle. If no event horizon intrusion occurs, translational velocity is set as a ratio of a speed factor relative to a maximum speed.


