Team Delft's Robot Winner of the Amazon Picking Challenge 2016

By Carlos Hernandez, M. Bharatheesha, W. Ko, H. Gaiser, Jethro Tan, K. V. Deurzen, M. D. Vries, B. V. Mil, J. V. Egmond, R. Burger and 6 more. 2016

162 citations recorded by the source corpus.

This paper describes Team Delft’s robot, which won the Amazon Picking Challenge 2016, including both the Picking and the Stowing competitions. The goal of the challenge is to automate pick and place operations in unstructured environments, specifically the shelves in an Amazon warehouse. Team Delft’s robot is based on an industrial robot arm, 3D cameras and a customized gripper. The robot’s software uses ROS to integrate off-the-shelf components and modules developed specifically for the competition, implementing Deep Learning and other AI techniques for object recognition and pose estimation, grasp planning and motion planning. This paper describes the main components in the system, and discusses its performance and results at the Amazon Picking Challenge 2016 finals.

Subfields: Computer Science Applications, Computer Vision and Pattern Recognition, Mechanical Engineering, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Science Applications

In Computer Vision and Pattern Recognition

In Mechanical Engineering

In Robotics & Control

Citations in the corpus

Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics (2017, methodology): “Precomputed grasps are indexed using point cloud registration: matching point clouds to known 3D object models in the database using visual and geometric similarity [4, 5, 8, 14, 21, 23, 28] and executing the highest quality grasp for the estimated object instance.”
Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks (2018, methodology): “with stored objects based on visual and geometric similarity [6, 11, 19, 20, 29].”
A self-supervised learning system for object detection using physics simulation and multi-view pose estimation (2017, unknown): “However, in the recently concluded Amazon Picking Challenge [3] where setup includes varying light conditions and cluttered objects, the top performing teams of TU Delft and MIT-Princeton developed vision system [6], [24] comprising of a CNN-based segmentation [11], [16] module followed by pairwise ”
Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching (2017, methodology): “05×n b a times reported from [20] derived from [3].”
Dex-Net 3.0: Computing Robust Vacuum Suction Grasp Targets in Point Clouds Using a New Analytic Model and Deep Learning (2018, background): “This defies our intuition since empirical evidence suggests that a single point of suction can robustly transport objects [6], [10].”
Learning ambidextrous robot grasping policies (2019, methodology): “To compare with hand-coded methods used in practice, we implemented a best-effort suction-only policy and an ambidextrous policy based on geometric heuristics similar to those used in the Amazon Robotics Challenge ( 29 , 30 , 32 ).”
Action Image Representation: Learning Scalable Deep Grasping Policies with Zero Real World Data (2020, background): “In order to execute these predicted grasps in the real world, the 3D object models have to be identified, located and their pose estimated [7], [8], [14], [5].”
Learning Visual Affordances for Robotic Manipulation (2019, methodology): “05×n b a times reported from [72] derived from [40].”