Laser Rangefinder and Monocular Camera Data Fusion for Human-Following Algorithm by PMB-2 Mobile Robot in Simulated Gazebo Environment

Chebotareva, Elvira; Hsia, Kuo-Hsien; Yakovlev, Konstantin; Magid, Evgeni

doi:10.1007/978-981-15-5580-0_29

Cited by 12 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 15 ] also uses convolutional channel features to first identify the target person and then follow the identified target person using the mobile robot. Both [ 15 ] and [ 26 ] first use laser range finder to track the person position, then Ref. [ 15 ] learns the convolutional-channel-features-based classifier to verify the target to follow, whereas Ref.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Lightweight Multimodal Domain Generic Person Reidentification Metric for Person-Following Robots

Syed

et al. 2023

Sensors

View full text Add to dashboard Cite

Recently, person-following robots have been increasingly used in many real-world applications, and they require robust and accurate person identification for tracking. Recent works proposed to use re-identification metrics for identification of the target person; however, these metrics suffer due to poor generalization, and due to impostors in nonlinear multi-modal world. This work learns a domain generic person re-identification to resolve real-world challenges and to identify the target person undergoing appearance changes when moving across different indoor and outdoor environments or domains. Our generic metric takes advantage of novel attention mechanism to learn deep cross-representations to address pose, viewpoint, and illumination variations, as well as jointly tackling impostors and style variations the target person randomly undergoes in various indoor and outdoor domains; thus, our generic metric attains higher recognition accuracy of target person identification in complex multi-modal open-set world, and attains 80.73% and 64.44% Rank-1 identification in multi-modal close-set PRID and VIPeR domains, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

“…[ 15 ] learns the convolutional-channel-features-based classifier to verify the target to follow, whereas Ref. [ 26 ] uses monocular camera to perform appearance matching. In another work [ 2 ], an online person classifier is also learned to track the target person, but in the robot coordinate space.…”

Section: Related Workmentioning

confidence: 99%

Lightweight Multimodal Domain Generic Person Reidentification Metric for Person-Following Robots

Syed

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In general, the Gazebo simulator is critical when a large number experiments is required, e.g., we successfully employed it for exhaustive simulation approach for a virtual camera calibration evaluation [46] and automated fiducial marker comparison in the Gazebo environment [47]. The Gazebo could be successfully applied in humanrobot related activities preliminary studies, e.g., humanfollowing by a mobile robot in an indoor scenario [48] (which was initially tested in a virtual world and then validated in real world experiments [49]) or robot control using gestures [50]. The Gazebo simulator significantly facilitated a preparatory stage of real-world experiments in a humanoid robot assisted English language teaching [51], which allowed saving time and resources both for our research team and for experiments' participants.…”

Section: Activities Modelling In a Virtual World Of The Gazebomentioning

confidence: 99%

Simulation Tools for Urban Search and Rescue Robotics

Magid

2023

Proceedings of International Conference on Artificial Life and Robotics

View full text Add to dashboard Cite

Real world experiments are critical for validating performance of new concepts and algorithms in robotics field. Yet, experiments tend to be too expensive in terms of time and resources of a research team. Moreover, it is not feasible to conduct thousands of complex experiments with a physical robot in a real environment. To check new ideas, preliminary evaluate new algorithms and interaction protocols, on first stages of a research project it is reasonable to start within a simulation. To produce relevant results, a simulator should provide adequate models of robots and environments with realistic physical properties. This paper presents an overview of our experience in using robot operating system (ROS) with Gazebo and Webots simulators for urban search and rescue robotics projects and considers constructing new models of mobile robots and complicated environments, algorithm validation and comparative analysis.

show abstract

“…However, to test novel navigation algorithms for AMRs in pedestrian rich environments, there is a need for a holistic simulator that combines the capabilities of these two types of simulators. Currently, to test these algorithms, the researchers rely on either testing directly in real environments as in [18] and [19] or spend significant time in building their own simulation environments as in [20] and [21]. Therefore, there is a clear need to have more open source simulators that are available for researchers to use for testing mobile robots in human rich environments.…”

Section: Motivation and Backgroundmentioning

confidence: 99%

Simulators for Mobile Social Robots:State-of-the-Art and Challenges

Kaur¹,

Liu²,

Shi³

2022

Preprint

View full text Add to dashboard Cite

The future robots are expected to work in a shared physical space with humans [1], however, the presence of humans leads to a dynamic environment that is challenging for mobile robots to navigate. The path planning algorithms designed to navigate a collision free path in complex human environments are often tested in real environments due to the lack of simulation frameworks. This paper identifies key requirements for an ideal simulator for this task, evaluates existing simulation frameworks and most importantly, it identifies the challenges and limitations of the existing simulation techniques.First and foremost, we recognize that the simulators needed for the purpose of testing mobile robots designed for human environments are unique as they must model realistic pedestrian behavior in addition to the modelling of mobile robots. Our study finds that Pedsim ros [2] and a more recent SocNavBench framework [3] are the only two 3D simulation frameworks that meet most of the key requirements defined in our paper. In summary, we identify the need for developing more simulators that offer an ability to create realistic 3D pedestrian rich virtual environments along with the flexibility of designing complex robots and their sensor models from scratch.

show abstract

Laser Rangefinder and Monocular Camera Data Fusion for Human-Following Algorithm by PMB-2 Mobile Robot in Simulated Gazebo Environment

Cited by 12 publications

References 23 publications

Lightweight Multimodal Domain Generic Person Reidentification Metric for Person-Following Robots

Lightweight Multimodal Domain Generic Person Reidentification Metric for Person-Following Robots

Simulation Tools for Urban Search and Rescue Robotics

Simulators for Mobile Social Robots:State-of-the-Art and Challenges

Contact Info

Product

Resources

About