Excavator Terrain Estimation Using Linkage Sensors and Touchpoints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous excavation systems rely on costly depth-perception technologies like LIDAR, which are prone to failure in noisy environments and do not allow remote operators to effectively interact with or visualize the terrain surface, making autonomous dig operations difficult and time-consuming.
Innovation Solution
The use of proprioception through linkage sensors to estimate and visualize the terrain surface, generating three-dimensional coordinates from touchpoints and projecting them onto a two-dimensional image plane to augment the camera view, allowing for improved terrain representation and operator interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If depth-perception systems (LIDAR, RADAR) are used to sense terrain in three dimensions, then autonomous excavation capability is improved, but system cost increases and reliability decreases in noisy environments
Solution Approach 1:
The patent replaces optical/electromagnetic sensing systems (LIDAR, RADAR) with a mechanical sensing approach using proprioception from machine sensors and linkage sensors. This substitution eliminates the vulnerability to dust and electromagnetic interference while maintaining autonomous excavation capability through mechanical measurement of the terrain surface.
Solution Approach 2:
The patent creates a digital copy or model of the terrain surface by collecting touchpoints through machine sensors and linkage sensors. This digital terrain model allows the system to sense and map the three-dimensional terrain without requiring physical depth-perception sensors, thereby improving reliability in noisy environments.
2Extent of automation
If depth-perception systems are used to enable autonomous digging, then excavation automation is improved, but system cost increases
Solution Approach 1:
The patent replaces expensive optical/electromagnetic sensing systems with existing mechanical sensors already present on the excavator (linkage sensors, machine sensors). This substitution dramatically reduces system cost while maintaining autonomous digging capability by using the mechanical measurement data to construct a digital terrain model.
Solution Approach 2:
The patent makes existing machine sensors and linkage sensors serve multiple functions: their primary function for machine operation control is maintained, and they additionally function as terrain sensing devices. This multi-functionality eliminates the need for dedicated expensive depth-perception sensors, thereby reducing system cost.
3Device complexity
If only a two-dimensional camera view is provided to the remote operator, then system simplicity is maintained, but operator ability to interact with and correct terrain estimates is reduced
Solution Approach 1:
The patent enhances the two-dimensional camera view by overlaying three-dimensional terrain surface information derived from touchpoints. This dimensional enhancement allows the operator to perceive depth and terrain features while maintaining the simple camera interface, thereby improving interaction capability without significantly increasing system complexity.
Solution Approach 2:
The patent introduces a digital terrain model as an intermediary between the physical terrain and the operator's camera view. This intermediary layer provides additional information about the terrain surface, enabling the operator to better understand and correct terrain estimates while keeping the interface relatively simple.
Data Source
AI summary
Autonomous systems enable a machine, such as an excavator, to dig in a specified area with little to no human intervention. However, conventional autonomous systems require costly exteroceptive systems to monitor the terrain surface during the autonomous dig operation. Accordingly, embodiments are disclosed for estimating a terrain surface using only proprioceptive sensors, such as the linkage sensors on the work implement of an excavator. The terrain surface may be estimated by fitting a surface to one or more touchpoints collected using the work implement. The estimated terrain surface may be updated during a dig operation using a model of material flow and/or by collecting additional touchpoints. Embodiments enable a remote operator to visualize this terrain surface in a camera view by projecting the estimated terrain surface onto an image plane with a representation that depicts one or more terrain parameters.