Rahul Shome

A Dataset for Improved RGBD-Based Object Detection and Pose Estimation for Warehouse Pick-and-Place

An important logistics application of robotics involves manipulators that pick-and-place objects placed in warehouse shelves. A critical aspect of this task corresponds to detecting the pose of a known object in the shelf using visual data. Solving this problem can be assisted by the use of an RGBD sensor, which also provides depth information beyond visual data. Nevertheless, it remains a challenging problem since multiple issues need to be addressed, such as low illumination inside shelves, clutter, texture-less and reflective objects as well as the limitations of depth sensors. This letter provides a new rich dataset for advancing the state-of-the-art in RGBD-based 3D object pose estimation, which is focused on the challenges that arise when solving warehouse pick-and-place tasks. The publicly available dataset includes thousands of images and corresponding ground truth data for the objects used during the first Amazon Picking Challenge at different poses and clutter conditions. Each image is accompanied with ground truth information to assist in the evaluation of algorithms for object detection. To show the utility of the dataset, a recent algorithm for RGBD-based pose estimation is evaluated in this letter. Given the measured performance of the algorithm on the dataset, this letter shows how it is possible to devise modifications and improvements to increase the accuracy of pose estimation algorithms. This process can be easily applied to a variety of different methodologies for object pose detection and improve performance in the domain of warehouse pick-and-place.

Cloud Automation: Precomputing Roadmaps for Flexible Manipulation

The goal of this article is to highlight the benefits of cloud automation for industrial adopters and some of the research challenges that must be addressed in this process. The focus is on the use of cloud computing for efficiently planning the motion of new robot manipulators designed for flexible manufacturing floors. In particular, different ways that a robot can interact with a computing cloud are considered, where an architecture that splits computation between the remote cloud and the robot appears advantageous. Given this synergistic robot-cloud architecture, this article describes how solutions from the recent literature can be employed on the cloud during a periodically updated preprocessing phase to efficiently answer manipulation queries on the robot given changes in the workspace. In this setup, interesting tradeoffs arise between path quality and computational efficiency, which are evaluated through simulation. These tradeoffs motivate further research on how motion planning should be executed given access to a computing cloud.

An Experimental Study for Identifying Features of Legible Manipulator Paths

This work performs an experimental study on the legibility of paths executed by a manipulation arm available on a Baxter robot. In this context, legibility is defined as the ability of people to effectively predict the target of the arm’s motion. Paths that are legible can improve the collaboration of robots with humans since they allow people to intuitively understand the robot’s intentions. Each experimental trial in this study reproduces manipulator motions to one of many targets in front of the robot. An appropriate experimental setup was developed in order to collect the responses of people in terms of the perceived robot’s target during the execution of a trajectory by Baxter. The objective of the experimental setup was to minimize the cognitive load of the human subjects during the collection of data. The extensive experimental data provide insights into the features of motion that make certain paths more legible for humans than other paths. For instance, motions where the end-effector is oriented towards the intended target appear to be better in terms of legibility than alternatives.

Rearranging similar objects with a manipulator using pebble graphs

This work proposes a method for efficiently computing manipulation paths to rearrange similar objects in a cluttered space. Rearrangement is a challenging problem as it involves combinatorially large, continuous configuration spaces due to the presence of multiple bodies and kinematically complex manipulators. This work leverages ideas from multi-robot motion planning and manipulation planning to propose appropriate graphical representations for this challenge. These representations allow to quickly reason whether manipulation paths allow the transition between entire sets of object arrangements without having to explicitly store these arrangements. The proposed method also takes advantage of precomputation given a manipulation roadmap for transferring a single object in the space. The approach is evaluated in simulation for a realistic model of a Baxter robot and executed on the real system, showing that the method solves complex instances and is promising in terms of scalability and success ratio.

An Extensible Software Architecture for Composing Motion and Task Planners

This paper describes a software infrastructure for developing and composing task and motion planners. The functionality of motion planners is well defined and they provide a basic primitive on top of which it is possible to develop planners for addressing higher level tasks. It is more challenging, however, to identify a common interface for task planners, given the variety of challenges that they can be used for. The proposed software platform follows a hierarchical, object-oriented structure and identifies key abstractions that help in integrating new task planners with popular sampling-based motion planners. Examples of use cases that can be implemented within this common software framework include robotics applications such as planning among dynamic obstacles, object manipulation and rearrangement, as well as decentralized motion coordination. The described platform has been used to plan for a Baxter robot rearranging similar objects in an environment in an efficient way.

Evaluating end-effector modalities for warehouse picking: A vacuum gripper vs a 3-finger underactuated hand

This paper studies two end-effector modalities for warehouse picking: (i) a recently developed, underactuated three-finger hand and (ii) a custom built, vacuum-based gripper. The two systems differ on how they pick objects. The first tool provides increased flexibility, while the vacuum alternative is simpler and smaller. The aim is to show how the end-effector influences the success rate and speed of robotic picking. For the study, the same planning process is followed for known poses of multiple objects with different geometries and characteristics. The resulting trajectories are executed on a real system showing that, under different conditions, different types of end-effectors can be beneficial. This motivates the development of hybrid solutions.