Cartman: The Low-Cost Cartesian Manipulator that Won the Amazon Robotics Challenge

By Douglas Morrison, Adam W. Tow, M. McTaggart, R. Smith, N. Kelly-Boxall, S. Wade-McCue, J. Erskine, R. Grinover, A. Gurman, T. Hunn and 12 more. 2017

147 citations recorded by the source corpus.

Ahstract-The Amazon Robotics Challenge enlisted sixteen teams to each design a pick-and-place robot for autonomous warehousing, addressing development in robotic vision and manipulation. This paper presents the design of our custom-built, cost-effective, Cartesian robot system Cartman, which won first place in the competition finals by stowing 14 (out of 16) and picking all 9 items in 27 minutes, scoring a total of 272 points. We highlight our experience-centred design methodology and key aspects of our system that contributed to our competitiveness. We believe these aspects are crucial to building robust and effective robotic systems.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Mechanical Engineering

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Mechanical Engineering

Citations in the corpus

QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation (2018, background): “However, current grasping systems typically approach the grasping task as the problem of predicting a grasp pose, where the system looks at the scene (typically using a depth camera), chooses the best location at which to grasp, and then executes an open-loop planner to reach that location [5, 6, 7,”
RLBench: The Robot Learning Benchmark & Learning Environment (2019, background): “cup end-effector [27], it was difficult to reproduce in a lab setup.”
TossingBot: Learning to Throw Arbitrary Objects With Residual Physics (2019, methodology): “In Table IV, we compare against other state-of-the-art picking systems found in literature: Cartman [24], Dex-Net 2.”
Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks (2018, background): “…systems typically either operate in an open-loop style, where grasping locations are chosen, and then a motion is executed to complete the grasp [69, 41, 37, 60], or in a closed-loop manner, where grasp prediction is continuously run during motion, either explicitly [65], or implicitly [27].”
Learning robust, real-time, reactive robotic grasping (2019, methodology): “To determine the best network configuration, we compare relative performance between our trained networks by evaluating each on detecting ground-truth grasps on a 20% evaluation dataset containing 1,710 augmented images from the Cornell Grasping Dataset.”
Learning task-oriented grasping for tool manipulation from simulated self-supervision (2018, background): “These learning methods largely fall into two families depending on the source of supervision: (1) supervised learning approaches (Herzog et al., 2012; Kroemer et al., 2012; Lenz et al., 2015; Mahler et al., 2017; Morrison et al., 2018; Saxena et al., 2008; ten Pas, et al., 2017), where the models ar”
Learning Visual Affordances for Robotic Manipulation (2019, background): “Among the competing teams, we successfully picked the most objects in the Stow and Final Tasks, and our average picking speed was the highest [79].”
Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching (2017, background): “Among the competing teams, we successfully picked the most objects in the stow and final tasks, and our average picking speed was the highest (Morrison et al., 2018).”
Learning ambidextrous robot grasping policies (2019, methodology): “In applications such as the Amazon Robotics Challenge, it is common to expand range by equipping robots with more than one end effector (e.g., both a parallel-jaw gripper and a suction cup).”
Dex-Net 3.0: Computing Robust Vacuum Suction Grasp Targets in Point Clouds Using a New Analytic Model and Deep Learning (2018, methodology): “In 2017, Cartman [23] won the challenge and ranked suction grasps according to heuristics such as maximizing distance to the segmented object boundary and MIT [35] performed well using a neural network trained to predict grasp affordance maps from human labeled RGB-D point clouds.”
PyRep: Bringing V-REP to Deep Robot Learning (2019, background): “Robotics has beneﬁted greatly from this progress, with many robotics systems opting to use deep learning in many or all of the processing stages of a typical robotics pipeline [2, 3].”