• Corpus ID: 1180870

Multiple Object Detection, Tracking and Long-Term Dynamics Learning in Large 3D Maps

  title={Multiple Object Detection, Tracking and Long-Term Dynamics Learning in Large 3D Maps},
  author={Nils Bore and Patric Jensfelt and John Folkesson},
In this work, we present a method for tracking and learning the dynamics of all objects in a large scale robot environment. A mobile robot patrols the environment and visits the different locations ... 
Detection, Tracking and 3D Modeling of Objects with Sparse RGB-D SLAM and Interactive Perception
An interactive perception system that enables an autonomous agent to deliberately interact with its environment and produce 3D object models using a novel segment classification scheme that allows the system to handle incorrect object hypotheses, common in cluttered environments due to touching objects or occlusion.
Towards Life-Long Autonomy of Mobile Robots Through Feature-Based Change Detection
A novel method for change detection based on the similarity of local visual features to distinguish important stable regions of the scene from the regions that are changing that substantially improves the accuracy of the robot localization, compared to using the baseline localization method without change detection.
Semantic Mapping with Simultaneous Object Detection and Localization
This work presents a filtering-based method for semantic mapping to simultaneously detect objects and localize their 6 degree-of-freedom pose and demonstrates that the particle filtering based inference of CT-Map provides improved object detection and pose estimation with respect to baseline methods.
SeanNet: Semantic Understanding Network for Localization Under Object Dynamics
It is demonstrated that SeanNet outperforms all baseline methods, by robustly localizing the robot under object dynamics, thus reliably informing visual navigation about the task status, and develops a similarity-based localization method based on SeanNet for monitoring the progress of visual navigation tasks.
Artificial Intelligence for Long-Term Robot Autonomy: A Survey
This letter surveys and discusses AI techniques as “enablers” for long-term robot autonomy, current progress in integrating these techniques within long-running robotic systems, and the future challenges and opportunities for AI in long- term autonomy.
Critical Design and Control Issues of Indoor Autonomous Mobile Robots: A Review
These essential factors of autonomous mobile robots in terms of mathematical modeling, control issues, and challenging factors are surveyed and promising directions to guide the construction of an autonomous mobile robot with high accuracy and effectiveness are provided.
Chapter 6 Intelligent Robotic Perception Systems
This chapter will cover recent and emerging topics and use-cases related to intelligent perception systems in robotics.
Intelligent Robotic Perception Systems
This chapter will cover recent and emerging topics and use-cases related to intelligent perception systems in robotics.
Collaborative Robots: Development of Robotic Perception System, Safety Issues, and Integration of AI to Imitate Human Behavior
To take full advantage of this collaboration between robots and humans, the authors must understand how humans can most effectively augment robots and how robots can enhance what humans do best.


Detection and Tracking of General Movable Objects in Large 3D Maps
This paper studies the problem of detection and tracking of general objects with long-term dynamics, observed by a mobile robot moving in a large environment, and finds that due to the environs, this problem is difficult to solve.
Simultaneous localization and mapping with detection and tracking of moving objects
  • C. Wang, C. Thorpe
  • Computer Science
    Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292)
  • 2002
This paper presents a new method to integrate SLAM and DTMO to solve both problems simultaneously for both indoor and outdoor applications and confirms that they can be complementary to one another.
Unsupervised learning of spatial-temporal models of objects in a long-term autonomy scenario
The Meta-Room method is extended and evaluated on a complex dataset acquired autonomously by a mobile robot over a period of 30 days and it is shown that using the spatial-temporal information further increases the matching accuracy.
Conditional particle filters for simultaneous mobile robot localization and people-tracking
Presents a probabilistic algorithm for simultaneously estimating the pose of a mobile robot and the positions of nearby people in a previously mapped environment. This approach, called the
Temporal persistence modeling for object search
It is shown that probabilistic exponential distributions augmented with a Gaussian component can accurately represent probable object locations and search suggestions based entirely on sparsely made visual observations and contributes temporal persistence modeling (TPM), an algorithm for Probabilistic prediction of the time that an object is expected to remain at a given location given sparse prior observations.
Towards Mapping Dynamic Environments
An algorithm for mapping dynamic environments based on maintaining two occupancy grids in parallel that provides a complete description of the environment over time and applies a size-based classifier to the cells in the dynamic map to detect and track moving objects.
SLAM with object discovery, modeling and mapping
This work proposes an approach for online object discovery and object modeling, and extends a SLAM system to utilize these discovered and modeled objects as landmarks to help localize the robot in an online manner, as well as to improve SLAM results by detecting loop closures.
Simultaneous Localization, Mapping and Moving Object Tracking
Based on the SLAM with DATMO framework, practical algorithms are proposed which deal with issues of perception modeling, data association, and moving object detection.
Rao-Blackwellized particle filter for multiple target tracking
GATMO: A Generalized Approach to Tracking Movable Objects
We present GATMO (Generalized Approach to Tracking Movable Objects), a system for localization and mapping that incorporates the dynamic nature of the environment while maintaining semantic labels.