Delivery Robot Navigation Using AV-Aided 3D Augmented Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robot navigation in complex environments, such as urban areas, faces challenges due to limited sensing and computing capabilities, particularly in the last 100 meters of delivery where high-resolution maps may not be available, and dynamic obstacles like pedestrians and animals are encountered.
Innovation Solution
An autonomous vehicle (AV) integrates with a delivery robot, providing extended sensing capabilities by identifying key features and obstacles, and relaying unified map data to the robot, which uses infrastructure sensors and onboard systems for navigation, obstacle detection, and classification, enabling improved path planning and localization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the delivery robot uses its own onboard sensing system, then it can independently navigate, but the sensing range and resolution are insufficient for complex urban environments
Solution Approach 1:
The patent combines the AV's advanced sensing system with the delivery robot's onboard sensors to create a unified sensing framework. The AV's sensors detect obstacles and map the environment at a broader scale, while the robot's sensors provide fine-grained local perception, together achieving comprehensive sensing precision without requiring the robot to independently handle all sensing complexities.
Solution Approach 2:
The AV acts as an intermediary that preprocesses environmental data and relays processed information to the delivery robot. This mediator role allows the robot to benefit from the AV's advanced sensing capabilities without directly managing the complexity of processing raw sensor data from multiple sources.
2Reliability
If the delivery robot operates independently with limited compute, then it maintains simplicity, but navigation and obstacle detection in dynamic environments become unreliable
Solution Approach 1:
The AV performs preliminary actions by pre-mapping the delivery environment and identifying key features and obstacles before the robot begins its journey. This advance preparation creates a reliable navigation framework that the robot can follow, improving navigation reliability without requiring the robot to have complex real-time decision-making capabilities.
Solution Approach 2:
The system implements feedback loops where the AV continuously monitors the robot's position and the changing environment, then relays updated information to the robot. This feedback mechanism ensures the robot maintains reliable navigation in dynamic environments by receiving real-time updates about obstacles and path changes without the robot needing to independently process all environmental variables.
3Measurement precision
If high-resolution maps are available, then precise navigation is possible, but map availability in varied delivery locations cannot be guaranteed
Solution Approach 1:
The system dynamically adapts to different delivery locations by having the AV perform on-demand environmental scanning and map generation. When high-resolution maps are unavailable, the AV dynamically creates local maps of the delivery environment and relays this information to the robot, enabling precise localization and navigation in previously unvisited or changed environments.
Solution Approach 2:
The AV performs preliminary environmental assessment and map generation at each delivery location before the robot arrives. This advance preparation ensures that high-resolution local maps are available when needed, enabling precise navigation even in locations where pre-existing maps were not available.
Data Source
AI summary
A method for controlling a robotic vehicle in a delivery environment includes causing the robotic vehicle to deploy from an autonomous vehicle (AV) at a first AV position in the delivery environment. The method further includes localizing, via a robotic vehicle controller, an initial position within a global reference map using a robot vehicle perception system, receiving, from the AV, a 3-dimensional (3D) augmented map and localizing an updated position in the delivery environment based on the 3D augmented map and the global reference map. The robot vehicle perception system senses obstacle characteristics, and generates a unified 3D augmented map with robot-sensed obstacle characteristics. The method further includes generating a dynamic path plan to a package delivery destination using the unified 3D augmented map, and actuating the robot vehicle to the package delivery destination according to the dynamic path plan.