# A Single Multi-Task Deep Neural Network with Post-Processing for Object Detection with Reasoning and Robotic Grasp Detection

arXiv: https://arxiv.org/abs/1909.07050 · HTML: https://mlsanity.com/paper/1909.07050/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2019.

## Built on by (most cited first, 8 of 8)

- [End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB](https://mlsanity.com/paper/2107.05287/) (2021)
- [Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Camera](https://mlsanity.com/paper/2309.09297/) (2023)
- [Depth-aware Object Segmentation and Grasp Detection for Robotic Picking Tasks](https://mlsanity.com/paper/2111.11114/) (2021)
- [AGILE: Approach-based Grasp Inference Learned from Element Decomposition](https://mlsanity.com/paper/2402.01303/) (2024)
- [A Modern Take on Visual Relationship Reasoning for Grasp Planning](https://mlsanity.com/paper/2409.02035/) (2024)
- [Real-World Semantic Grasp Detection Based on Attention Mechanism](https://mlsanity.com/paper/2111.10522/) (2021)
- [Evaluating Gaussian Grasp Maps for Generative Grasping Models](https://mlsanity.com/paper/2206.00432/) (2022)
- [Modular Anti-noise Deep Learning Network for Robotic Grasp Detection Based on RGB Images](https://mlsanity.com/paper/2310.19223/) (2023)

## Abstract (arXiv)

Recently, robotic grasp detection (GD) and object detection (OD) with reasoning have been investigated using deep neural networks (DNNs). There have been works to combine these multi-tasks using separate networks so that robots can deal with situations of grasping specific target objects in the cluttered, stacked, complex piles of novel objects from a single RGB-D camera. We propose a single multi-task DNN that yields the information on GD, OD and relationship reasoning among objects with a simple post-processing. Our proposed methods yielded state-of-the-art performance with the accuracy of 98.6% and 74.2% and the computation speed of 33 and 62 frame per second on VMRD and Cornell datasets, respectively. Our methods also yielded 95.3% grasp success rate for single novel object grasping with a 4-axis robot arm and 86.7% grasp success rate in cluttered novel objects with a Baxter robot.