Perspectives on standardization in mobile robot programming: the Carnegie Mellon Navigation (CARMEN) Toolkit

By Michael Montemerlo, Nicholas A. Roy, Sebastian Thrun. IEEE/RJS International Conference on Intelligent RObots and Systems, 2003

445 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/df706d522e23a32cbc76361538ebb910999be255

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

LCM: Lightweight Communications and Marshalling (2010, methodology): “We direct our attention specifically towards its use in developing robotic systems, where the idea of dividing large systems into modules has become commonplace [2], [3].”
PIXHAWK: A micro aerial vehicle design for autonomous flight using onboard computer vision (2012, methodology): “CARMEN and CLARAty have paved the way for standardized robotics toolkits, but their use has declined with the wide adoption of ROS.”
Learning Relational Navigation Policies (2006, methodology): “To execute the navigation plans on the robot and in simulation runs, we used the Robot Navigation Toolkit CARMEN [25].”
Identifiable Experiment Code And Configuration Is Important , Good and Easy (2010, unknown): “Various free-to-use middleware and simulartion platforms for robotics have been used over the last fifteen years, of which Carmen[7], Player[8] and recently ROS(6) are probably the most influential in research.”
Improved Techniques for Grid Mapping With Rao-Blackwellized Particle Filters (2007, methodology): “In our implementation, we use the scan-matcher “vasco,” which is part of the Carnegie Mellon Robot Navigation Toolkit (CARMEN) [20], [21].”
Development environments for autonomous mobile robots: A survey (2007, methodology): “…All the systems under consideration are neutral with regard to agent architectures, although MissionLab has a strong association with the AuRA architecture (Arkin and Balch, 1997) and CARMEN has been described by its authors as an example of the 3T hybrid architecture (Montemerlo et al., 2003b).”
Learning decisions: robustness, uncertainty, and approximation (2004, methodology): “We developed a new planner for the CARMEN [Montemerlo et al., 2003] project, modeling a dynamic obstacle in the robot’s path in the uncertain MDP framework.”
Robot Operating System 2: Design, architecture, and uses in the wild (2022, methodology): “For example, Carnegie Mellon Robot Navigation Toolkit (CARMEN) was built on TCA’s message-passing system called IPC (interprocess communications) (13, 14).”
Anytime Point-Based Approximations for Large POMDPs (2006, methodology): “To verify the robustness of our approach, the final PBVI control policy was implemented and tested onboard the publicly available CARMEN robot simulator (Montemerlo et al., 2003).”
Real-time correlative scan matching (2009, methodology): “We follow the approach of previous approaches [18], [19] by pre-computing a lookup table containing log probabilities of lidar observation at each ( x, y ) position in the world.”
A Fully Autonomous Indoor Quadrotor (2012, background): “Several effective systems for indoor and outdoor navigation of ground vehicles are currently available [1], [2].”
The Graph SLAM Algorithm with Applications to Large-Scale Mapping of Urban Structures (2006, methodology): “We have, on several occasions, used our navigation package Carmen ( Montemerlo, Roy, and Thrun 2003 ) to drive the robot autonomously, validating the terrain analysis techniques discussed above.”
ROS: an open-source Robot Operating System (2009, background): “Although frameworks based on a central server (e.g., CARMEN [4]) can also realize the benefits of the multi-process and multi-host design, a central data server is problematic if the computers are connected in a heterogenous network.”
Core Challenges of Social Robot Navigation: A Survey (2021, background): “In fact, their underlying navigation frameworks [74, 179] treated humans as non-reactive obstacles without explicitly modeling human navigation, social engagement, or interaction with and between humans.”
YARP: Yet Another Robot Platform (2006, background): “Somewhat similar projects have evolved from other domains in robotics such as mobile navigation (Carmen/IPC [15]) and commercial/industrial robotics (Orocos [16]), and we expect that there will be further development as the perceptual component of robotics grows in importance.”