High-Speed Detector for Low-Powered Devices in Aerial Grasping

Ashish Kumar, Laxmidhar Behera

Abstract: Autonomous aerial harvesting is a highly complex problem because it requires numerous interdisciplinary algorithms to be executed on mini low-powered computing devices. Object detection is one such algorithm that is compute-hungry. In this context, we make the following contributions: ( i ) Fast Fruit Detector (FFD), a resource-efficient, single-stage, and postprocessing-free object detector based on our novel latent object representation ( LOR ) module, query assignment, and prediction strategy. FFD achieves $\mathbf {100}$ FPS $@$ FP $\mathbf {32}$ precision on the latest $\mathbf {10}$ W NVIDIA Jetson-NX embedded device while co-existing with other time-critical sub-systems such as control, grasping, SLAM, a major achievement of this work, ( ii ) a method to generate vast amounts of training data without exhaustive manual labelling of fruit images since they consist of a large number of instances, which increases the labelling cost and time, and ( iii ) an open-source fruit detection dataset having plenty of very small-sized instances that are difficult to detect. Our exhaustive evaluations on our and MinneApple dataset show that FFD, being only a single-scale detector, is more accurate than many representative detectors, e.g. FFD is better than single-scale Faster-RCNN by $\mathbf {10.7}$ AP, multi-scale Faster-RCNN by $\mathbf {2.3}$ AP, and better than latest single-scale YOLO-v $\mathbf {8}$ by $\mathbf {8}$ AP and multi-scale YOLO-v $\mathbf {8}$ by $\mathbf {0.3}$ while being considerably faster.