ROS for Human-Robot Interaction (or ROS4HRI [ros4hri]) is the main API that
your robot implements to represent information about the human surrounding
and interacting with the robot.
ROS4HRI actually refers to a set of conventions and tools that help developing
Human-Robot Interaction capabilities. The specification (originally developed by
PAL Robotics) is available online as the ROS REP-155.
The ROS4HRI API defines several types of identifiers (IDs)¶
We have implemented the following main parts of the specification in your robot:
We follow the ROS4HRI human model representation, as a combination of a
permanent identity (person) and transient parts that are intermittently
detected (e.g. face, skeleton, voice);
In PAL OS edge, we specifically support:
face detection and recognition (including extraction of facial
landmarks);
single body detection, and 2D and 3D skeleton tracking;
speech recognition (without support for voice separation or voice
identification)
probabilistic fusion of faces, bodies and voices
We follow the ROS4HRI topic naming conventions, with all human-related
messages published under the /humans/ topic namespace;
We follow the ROS4HRI kinematic model of the human and 3D tf frame
conventions (naming, orientation), as specified here.
In addition, your robot also provides implementation for:
To ease access to these topics, you can use pyhri (Python) or libhri
(C++). These two open-source libraries are developed by PAL Robotics under an
Apache 2.0 license, and are available on GitHub:
https://github.com/ros4hri/libhri
Social perception with ROS4HRI¶
ROS for Human-Robot Interaction (or ROS4HRI [ros4hri]) is the main API that your robot implements to represent information about the human surrounding and interacting with the robot.
ROS4HRI actually refers to a set of conventions and tools that help developing Human-Robot Interaction capabilities. The specification (originally developed by PAL Robotics) is available online as the ROS REP-155.
The ROS4HRI API defines several types of identifiers (IDs)¶
We have implemented the following main parts of the specification in your robot:
We follow the ROS4HRI human model representation, as a combination of a permanent identity (person) and transient parts that are intermittently detected (e.g. face, skeleton, voice);
In PAL OS edge, we specifically support:
face detection and recognition (including extraction of facial landmarks);
single body detection, and 2D and 3D skeleton tracking;
speech recognition (without support for voice separation or voice identification)
probabilistic fusion of faces, bodies and voices
We follow the ROS4HRI topic naming conventions, with all human-related messages published under the
/humans/topic namespace;We follow the ROS4HRI kinematic model of the human and 3D tf frame conventions (naming, orientation), as specified here.
In addition, your robot also provides implementation for:
gaze estimation
automatic engagement detection
How to use ROS4HRI?¶
The ROS4HRI topics are documented in Social perception topics.
To ease access to these topics, you can use
pyhri(Python) orlibhri(C++). These two open-source libraries are developed by PAL Robotics under an Apache 2.0 license, and are available on GitHub: https://github.com/ros4hri/libhriNext steps¶
Get started with ROS4HRI and play with the social perception capabilities with the following tutorials:
How to launch the different components for person detection
How to access information of a face, a skeleton or a person?
Detect people oriented toward the robot (Python)
Detect people around the robot (C++)
See also¶
The REP-155 aka ROS4HRI specification, on ROS website.
The ROS wiki contains useful resources about ROS4HRI.
References¶
ROS for Human-Robot Interaction Y. Mohamed; S. Lemaignan, IROS 2021, doi: 10.1109/IROS51168.2021.9636816