The Marathon 2: A Navigation System

Macenski, Steve; Martı́n, Francisco; White, Ruffin; Clavero, Jonatan Ginés

doi:10.1109/iros45743.2020.9341207

Cited by 149 publications

(80 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was also selected as the new default SLAM vendor in ROS 2, the second generation of robot operating systems, replacing GMapping. SLAM Toolbox was integrated into the new ROS 2 Navigation2 project, providing real-time positioning in dynamic environments for autonomous navigation (Macenski, Martín, et al, 2020). It has been shown to map spaces as large as 24,000 m 2 , or 250,000 f t 2 , in real-time by non-expert technicians.…”

Section: This Package Slam_toolbox Is Open-source Under Anmentioning

confidence: 99%

SLAM Toolbox: SLAM for the dynamic world

Macenski¹,

Jambrečić²

2021

JOSS

Self Cite

View full text Add to dashboard Cite

Developments in the field of mobile robotics and autonomous driving have resulted in the use of robots and vehicles in retail stores, hospitals, warehouses, on the roads, and on sidewalks. These deployed areas are both dynamic and frequently massive in scale. The average size of a Walmart store is over 16,000 m 2 (Walmart, 2020) and a single square block in Chicago is over 21,000 m 2 (Heramb, 2007). Retail and warehouse spaces can change drastically throughout the year and the state of roadways can be changing by the hour. Much work has been made to address changing environments in robot perception (Macenski, Tsai, et al., 2020), but less has been built in open-source to represent maps of dynamic spaces.

show abstract

Section: This Package Slam_toolbox Is Open-source Under Anmentioning

confidence: 99%

SLAM Toolbox: SLAM for the dynamic world

Macenski¹,

Jambrečić²

2021

JOSS

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similar to MTC, we can enable the robot to explain if there is an obstacle on the ground blocking its path. Fortunately, we recently learned that the navigation stack in ROS 2 uses BTs to represent navigation behaviors [29], which paves the way for our explanation algorithms to be integrated into the navigation stack.…”

Section: Limitations and Future Workmentioning

confidence: 99%

“…Specifically, we base our work on Behavior Trees (BTs), which is a tree structure that encapsulates behavior by control nodes that contain child execution nodes. BTs [12] are a popular way to model the behavior of AI agents in the gaming industry (e.g., References [27,44]), but have also gained momentum in robotics, where they are used for end-user robot programming [40], deployed on a Rethink Robotics Sawyer robot [12], and applied to Learning from Demonstration [17] and navigation [29].…”

Section: Introductionmentioning

confidence: 99%

Building the Foundation of Robot Explanation Generation Using Behavior Trees

Han

Giger

Allspaw

et al. 2021

J. Hum.-Robot Interact.

View full text Add to dashboard Cite

As autonomous robots continue to be deployed near people, robots need to be able to explain their actions. In this article, we focus on organizing and representing complex tasks in a way that makes them readily explainable. Many actions consist of sub-actions, each of which may have several sub-actions of their own, and the robot must be able to represent these complex actions before it can explain them. To generate explanations for robot behavior, we propose using Behavior Trees (BTs), which are a powerful and rich tool for robot task specification and execution. However, for BTs to be used for robot explanations, their free-form, static structure must be adapted. In this work, we add structure to previously free-form BTs by framing them as a set of semantic sets {goal, subgoals, steps, actions} and subsequently build explanation generation algorithms that answer questions seeking causal information about robot behavior. We make BTs less static with an algorithm that inserts a subgoal that satisfies all dependencies. We evaluate our BTs for robot explanation generation in two domains: a kitting task to assemble a gearbox, and a taxi simulation. Code for the behavior trees (in XML) and all the algorithms is available at github.com/uml-robotics/robot-explanation-BTs.

show abstract

“…Researchers usually make use of cost function approach in conjunction with theory of proxemics to evaluate the distance between human and robot and take desired action (Charalampous et al, 2017). The visibility helps to form the social map, building on the criterion that robot must be in line of sight of human in order to eliminate the element of surprise (Khelloufi et al, 2020;Macenski et al, 2020), as shown in Figure 9.…”

Section: Social Mappingmentioning

confidence: 99%

“…Figure 9: Social mapping experiment in an indoor environment (Macenski et al, 2020) Many social mapping algorithms utilizes social force model (SFM) in outdoor environments to predict the human motion. SFM builds on the concept that human trajectories can be explained by social field and forces.…”

Section: Social Mappingmentioning

confidence: 99%

Understanding Socially Aware Robot Navigation

Singh

Kapoor

Sohi

2021

JER is an international, peer-reviewed journal that publishes f

View full text Add to dashboard Cite

Navigation is an essential skill for autonomous robots and it becomes a cumbersome task in human populated environments. Robots need to perform the tasks without disturbing the humans around them and ensure comfort and safety of humans as well. It is further influenced by various factors like social norms, geometry of environment and surrounding people. It is essential to comprehend three components i.e. Social Conventions (SC), Human Motion (HM) and Context Aware Mapping (CAM) for establishing effective socially aware robot navigation (SARN). This article discusses these different aspects of these components which should be taken into consideration while designing an efficient and optimal SARN. Further, it reports recent experiments conducted by different institutes pertaining to these components.

show abstract

The Marathon 2: A Navigation System

Cited by 149 publications

References 12 publications

SLAM Toolbox: SLAM for the dynamic world

SLAM Toolbox: SLAM for the dynamic world

Building the Foundation of Robot Explanation Generation Using Behavior Trees

Understanding Socially Aware Robot Navigation

Contact Info

Product

Resources

About