Semi-autonomous Mobile Device Obstacle Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile device control systems face challenges due to latency, safety concerns in dynamic environments, and complexity in navigating through tight spaces with obstacles, requiring users to provide numerous navigation commands to avoid collisions.
Innovation Solution
A semi-autonomous mobile device system that uses a depth camera to capture and process depth data into an obstacle map, combining user suggestions with collision avoidance technology to navigate through environments, incorporating infrared and sonar sensing for comprehensive obstacle detection and fusion, allowing the device to autonomously avoid collisions and adjust speed and direction accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If user provides navigation commands to control mobile device, then device can be driven through environment, but user latency causes poor path control and possible collisions
Solution Approach 1:
The mobile device performs self-navigation by autonomously detecting obstacles using depth cameras and other sensors, processing spatial information to generate navigation paths, and executing movement commands without continuous user intervention. The system serves itself by making real-time navigation decisions based on environmental perception.
Solution Approach 2:
The system continuously captures depth data and sensor information about the environment, processes this information to detect obstacles and calculate safe paths, then adjusts navigation commands in real-time based on this feedback loop. This closed-loop control enables the device to respond dynamically to changing conditions.
2Reliability
If user slows down device in tight spaces with obstacles, then collision risk decreases, but navigation efficiency and speed decrease
Solution Approach 1:
The system performs preliminary obstacle detection by continuously capturing depth data and processing spatial information before the device reaches potential collision points. By identifying obstacles in advance and pre-calculating safe paths, the device can maintain higher speeds while still avoiding collisions.
Solution Approach 2:
The navigation system dynamically adjusts the device's speed and path based on real-time environmental perception. The device accelerates in open spaces and automatically decelerates when obstacles are detected, creating a dynamic speed profile that optimizes both safety and efficiency rather than maintaining a constant slow speed.
3Speed
If depth camera processes data at high frame rate, then real-time obstacle detection improves, but computational load and energy consumption increase
Solution Approach 1:
The system segments the processing pipeline into distinct stages: depth data acquisition from cameras, spatial information processing to detect obstacles, and navigation command generation. Each stage processes only the necessary data for its specific function, reducing overall computational load while maintaining real-time performance.
Solution Approach 2:
The system extracts only the critical spatial information needed for collision avoidance from the full depth camera data stream. By identifying and processing only the relevant features (such as obstacle positions and distances) rather than analyzing every pixel, the computational energy requirement is significantly reduced while maintaining detection effectiveness.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system effectively reduces user latency issues, enhances safety by preventing collisions in dynamic environments, and simplifies navigation through tight spaces by allowing the device to make real-time decisions and adjust its path, ensuring smooth and safe operation even under high latency conditions.
Implementation Method 1
A depth camera (e.g., coupled to the robot) captures depth data
Implementation Method 2
fusing the depth camera-detected obstacle data with any other closer obstacle data as detected via infrared-based sensing
Implementation Method 3
fusing the depth camera-detected obstacle data with any other closer obstacle data as detected via sonar-based sensing
Data Source
AI summary
The subject disclosure is directed towards driving a robot or other mobile device safely through an environment by using a depth camera to obtain depth data, and then using the depth data for collision avoidance. Horizontal profile information may be built from the depth data, such as by collapsing a two-dimensional depth map into one-dimensional horizontal profile information. The horizontal profile information may be further processed by fusing the depth camera-detected obstacle data with any closer obstacle data as detected via infrared-based sensing and/or sonar-based sensing. Driving suggestions from a user or program are overridden as needed to avoid collisions, including by driving the robot towards an open space represented in the horizontal profile information, or stopping/slowing the robot as needed.