Herb 2.0: Lessons Learned From Developing a Mobile Manipulator for the Home

By Siddhartha S. Srinivasa, Dmitry Berenson, Maya Cakmak, Alvaro Collet, M. Dogar, Anca Dragan, Ross A. Knepper, T. Niemüller, Kyle Strabala, Michael Vande Weghe and 1 more. 2012

123 citations recorded by the source corpus.

We present the hardware design, software architecture, and core algorithms of Herb 2.0, a bimanual mobile manipulator developed at the Personal Robotics Lab at Carnegie Mellon University, Pittsburgh, PA. We have developed Herb 2.0 to perform useful tasks for and with people in human environments. We exploit two key paradigms in human environments: that they have structure that a robot can learn, adapt and exploit, and that they demand general-purpose capability in robotic systems. In this paper, we reveal some of the structure present in everyday environments that we have been able to harness for manipulation and interaction, comment on the particular challenges on working in human spaces, and describe some of the lessons we learned from extensively testing our integrated platform in kitchen and office environments.

Subfields: Computer Vision and Pattern Recognition, Mechanical Engineering, Social Psychology

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Mechanical Engineering

In Social Psychology

Citations in the corpus

Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection (2016, background): “In contrast, robotic manipulation often (though not always) relies more heavily on advance planning and analysis, with relatively simple feedback, such as trajectory following, to ensure stability during execution (Srinivasa et al., 2012).”
Shared autonomy via hindsight optimization for teleoperation and teaming (2017, methodology): ““HERB was a good partner” 2.”
Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocols (2015, methodology): “We executed this test on the HERB robot [60] as seen in Fig.”
Fetch & Freight : Standard Platforms for Service Robot Applications (2016, methodology): “has been created with a pair of Barrett WAM arms and a mobile base [8].”
Sampling-Based Robot Motion Planning: A Review (2014, background): “Certain planning dimensions are disregarded by constraining the motion of the robot to a specific manifold or moving the planning problem into a lower dimensional space that is more relevant the task [76], [167]–[169].”
Legibility and predictability of robot motion (2013, methodology): “We found, for instance, that different people expect a complex robot like HERB to act in different ways: for a robot to be predictable, it must adapt to the particulars of the observer.”
Toward seamless human-robot handovers (2013, methodology): “For the experiments presented in this section, we implemented and evaluated several versions of handover behaviors on our robot HERB (Home Exploring Robot Butler) (Srinivasa et al., 2012).”
Batch Informed Trees (BIT*): Sampling-based optimal planning via the heuristically guided search of implicit random geometric graphs (2014, methodology): “HERB’s proximity to the table and starting position created a narrow passage for the arms around the table.”
Teleoperation with intelligent and customizable interfaces (2013, methodology): “Then, the maximum curvature of the offset function o(X) occurs at an example point Xi, and is therefore c.”