Edge-Native Temporal--Graph Dual-Expert Inference for Dexterous Grasp Classification
Edge-Native Temporal--Graph Dual-Expert Inference for Dexterous Grasp Classification
This research proposes a dual-expert architecture, DualExpert, combining a Temporal Convolutional Network (TCN) and a Finger Graph Filter Network (FGFN), to classify grasped objects and predict finger-specific stop events using only joint-angle and actuator-load feedback. The system achieves 93.78% trajectory-level classification accuracy and 95.25% F1 score for stop prediction, with low inference latency suitable for edge deployment.
This paper introduces a dual-expert architecture for dexterous grasp classification using only joint-angle and actuator-load feedback, avoiding the need for dense tactile arrays. The system achieves high accuracy in both object classification and finger-specific stop prediction, with efficient inference times suitable for real-time deployment.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- dataset: not_reported
- code: not_reported
- weights: not_reported
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
m five object instances. In Flash deployment, mixed accelerator execution retains 93.78\% classification accuracy and 94.84\% Stop F1 with 2.890~ms mean inference time and 9.172~ms mean sample-to-stop latency. Across 50 physical trials, the system achieves 96.00\% recognition and 98.00\% grasp success while the complete embedded board draws approximately 0.80~W.
Open source S5
Stop probabilities, while the FGFN encodes finger topology and contributes only to object classification. Fixed 0.7/0.3 class-probability fusion reaches 93.78\% trajectory-level classification accuracy on 225 held-out trials, improving the standalone TCN and FGFN by 4.00 and 2.22 percentage points, respectively. The TCN Stop path attains 95.25\% F1. The dataset contains 1,500 automatically collected trajectories fro
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org