Online simultaneous localization and mapping with detection and tracking of moving objects: theory and results from a ground vehicle in crowded urban areas

By Chieh-Chih Bob Wang, C. Thorpe, Sebastian Thrun. IEEE International Conference on Robotics and Automation, 2003

387 citations recorded by the source corpus.

The simultaneous localization and mapping (SLAM) with detection and tracking of moving objects (DATMO) problem is not only to solve the SLAM problem in dynamic environments but also to detect and track these dynamic objects. In this paper, we derive the Bayesian formula of the SLAM with DATMO problem, which provides a solid basis for understanding and solving this problem. In addition, we provide a practical algorithm for performing DATMO from a moving platform equipped with range sensors. The probabilistic approach to solve the whole problem has been implemented with the Navlab11 vehicle. More than 100 miles of experiments in crowded urban areas indicated that SLAM with DATMO is indeed feasible.

Subfields: Aerospace Engineering, Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/161fbcb657cbb5ddff3d0d3d828f24f1362085d2

How researchers see this paper

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

In Aerospace Engineering

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM (2020, background): “Among them, Wang et al. [14] derived the Bayes formula of the SLAM with tracking of moving objects and provided a solid basis for understanding and solving this problem.”
The Graph SLAM Algorithm with Applications to Large-Scale Mapping of Urban Structures (2006, methodology): “They include photo-realistic rendering (Allen and Stamos 2000; Bajcsy, Kamberova, and Nocera 2000), surveillance (Wang, Thorpe, and Thrun 2003), scientific measurement (Baker et al. 2004), and robot guidance (Williams, Dissanayake, and Durrant-Whyte 2001).”
FastSLAM: a factored solution to the simultaneous localization and mapping problem (2002, methodology): “This approach has been used successfully by several authors in the scan-matching community [28, 74].”
Map-Based Precision Vehicle Localization in Urban Environments (2007, background): “SLAM addresses the problem of building consistent environment maps from a moving robotic vehicle, while simultaneously localizing the vehicle relative to these maps.”
MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM (2018, background): “Although dynamic SLAM has been studied for a couple of decades [6], approaches based on visual dense SLAM have only recently been explored.”
Persistent Navigation and Mapping using a Biologically Inspired SLAM System (2010, background): “Some research has extended existing SLAM algorithms to handle certain classes of dynamic objects such as people (Wang et al., 2003), or to detect and incorporate changes in a map (Biber and Duckett, 2005 Wolf and Sukhatme, 2005).”
Model-free detection and tracking of dynamic objects with 2D lidar (2015, background): “We note there exists a large body of work on similar application domains (for example, Miyasaka et al., 2009; Mertz et al., 2013; Wang et al., 2003), however it is often difficult to obtain a fair quantitative comparison with the methods due to either a lack of quantitative results or difficulty of ”
Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, neutral): “of Moving Objects) approaches [119]–[121].”
Multiple‐Robot Simultaneous Localization and Mapping: A Review (2016, methodology): “In these environments, SLAM is combined with detection and tracking (Wang et al., 2003).”
Simultaneous Localization, Mapping and Moving Object Tracking (2007, methodology): “Even with precise localization, it is not easy to solve the moving object tracking problem in crowded urban environments because of the wide variety of targets (Wang et al., 2003a).”
Simultaneous Localization and Mapping with Sparse Extended Information Filters (2004, background): “In SLAM, it is usually assumed that features do not change their location over time; see Hähnel et al. (2003c) and Wang, Thorpe, and Thrun (2003) for a treatment of SLAM in dynamic environments.”