Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge
This work addresses efficiency challenges for deploying multi-task vision systems in manufacturing and warehouse robotic arms, though it is incremental as it builds on existing network architecture search methods.
The authors tackled the problem of high computational complexity in multi-task learning for robotic grasping on embedded devices by proposing Fast GraspNeXt, which achieved the highest performance on the MetaGraspNet benchmark with 17.8M parameters, 259 GFLOPs, and >3.15x faster inference on an NVIDIA Jetson TX2.
Multi-task learning has shown considerable promise for improving the performance of deep learning-driven vision systems for the purpose of robotic grasping. However, high architectural and computational complexity can result in poor suitability for deployment on embedded devices that are typically leveraged in robotic arms for real-world manufacturing and warehouse environments. As such, the design of highly efficient multi-task deep neural network architectures tailored for computer vision tasks for robotic grasping on the edge is highly desired for widespread adoption in manufacturing environments. Motivated by this, we propose Fast GraspNeXt, a fast self-attention neural network architecture tailored for embedded multi-task learning in computer vision tasks for robotic grasping. To build Fast GraspNeXt, we leverage a generative network architecture search strategy with a set of architectural constraints customized to achieve a strong balance between multi-task learning performance and embedded inference efficiency. Experimental results on the MetaGraspNet benchmark dataset show that the Fast GraspNeXt network design achieves the highest performance (average precision (AP), accuracy, and mean squared error (MSE)) across multiple computer vision tasks when compared to other efficient multi-task network architecture designs, while having only 17.8M parameters (about >5x smaller), 259 GFLOPs (as much as >5x lower) and as much as >3.15x faster on a NVIDIA Jetson TX2 embedded processor.