Refuse Can Detection and Trajectory Planning for Safe Dumping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Refuse collection vehicles face challenges in efficiently detecting and engaging refuse cans, particularly in navigating to the correct position and securely grasping them, which can lead to inefficiencies and potential safety hazards, especially when human beings are present.
Innovation Solution
A system comprising sensors, an actuator assembly, and a controller that uses a single-stage object detector to identify refuse cans, determine their position, and generate trajectories for both the vehicle and the actuator assembly to engage the cans, while ensuring safety by preventing movement if humans are detected in the danger zone.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated detection and engagement systems are implemented, then productivity and safety are improved, but device complexity increases
Solution Approach 1:
The automated refuse collection system is divided into distinct functional modules: sensor subsystems for detection, processing subsystems for trajectory calculation, and actuator assemblies for engagement. This segmentation allows each component to be optimized independently while working together to improve overall productivity without proportionally increasing system complexity.
Solution Approach 2:
The system enables the refuse collection vehicle to automatically detect, track, and engage refuse cans without human intervention. The automated detection and engagement systems perform self-service functions, reducing labor requirements and improving productivity while the complexity is managed through standardized control architectures.
2Speed
If single-stage object detectors are used, then detection speed is improved, but measurement precision may be compromised
Solution Approach 1:
The single-stage object detector is pre-trained and configured to recognize refuse cans with high accuracy before actual detection begins. By preparing the detection model in advance with comprehensive training data, the system achieves both fast detection speed and high measurement precision during operation, eliminating the need for slower two-stage detection methods.
Solution Approach 2:
The detection system optimizes parameters such as confidence thresholds, detection scales, and processing resolutions to balance speed and precision. By dynamically adjusting these parameters based on operational conditions, the single-stage detector maintains high detection speed while achieving sufficient measurement precision for trajectory generation.
3Reliability
If multiple sensors are deployed to detect refuse cans and humans, then detection reliability is improved, but device complexity and cost increase
Solution Approach 1:
The sensor system uses multi-functional sensors that can detect both refuse cans and humans using the same detection framework. By designing sensors and processing algorithms that handle multiple object types universally, the system improves detection reliability for different targets without proportionally increasing device complexity.
Solution Approach 2:
The system employs an intermediary processing layer that standardizes data from multiple sensor sources before generating trajectories. This intermediary processing architecture allows multiple sensors to contribute to detection reliability while managing complexity through unified data fusion and object classification mechanisms.
Data Source
AI summary
A system for detecting and engaging a refuse can includes at least one sensor positioned on a refuse collection vehicle and configured to detect objects on one or more sides of the refuse vehicle, an actuator assembly configured to actuate to engage the refuse can, and a controller configured to detect, using a single-stage object detector, the presence of the refuse can based on first data received from the at least one sensor, determine, based on the first data, a position of the refuse can with respect to the refuse collection vehicle, generate a first trajectory from the refuse collection vehicle to the position of the refuse can, generate a second trajectory for the actuator assembly, and initiate a control action to move at least one of the refuse collection vehicle along the first trajectory or the actuator assembly along the second trajectory to engage the refuse can.