Platooning strategy of mobile robot: simulation and experiment

Baarath, K.; Zakaria, Muhammad Aizzat; Suparmaniam, M.V.; Abu, Mohd Yazid

doi:10.1051/matecconf/20179001060

Cited by 3 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a final drive test, one of the pedestrians was requested to walk in a random trajectory along a path that was not used for training or testing and the resulting behavior was recorded and posted here. 1 Due to wildfires in the vicinity when this drive test was conducted, an additional data set for training the classifier was required to account for the uncharacteristically smokey and hazy lighting conditions.…”

Section: A Random Walkmentioning

confidence: 99%

“…In Ref. [1], a state-space kinematic model is presented that uses a Kinect Ⓡ sensor to determine distance to the target object and adjusts velocity and trajectory to maintain a one meter distance while following. The common theme across much of this body of work is to minimize the complexity of the input signal while maximizing the responsiveness of the tracking vehicle by creating detailed mathematical representations that allow for the greatest flexibility in kinematic response.…”

Section: Introductionmentioning

confidence: 99%

“…Earlier efforts focused on creating robust kinematic models that require only minimal information from target objects, such as in Klancǎr et al [3], where a Euler integrable system of equations is fed the relative distance and angular trajectory of the target to force adherence to a tracking path. In Baarth et al [4], a state-space kinematic model is presented that uses a Kinect ® sensor to determine distance to the target object and adjust velocity and trajectory to maintain a one meter distance while following. The common theme across much of this body of work is to minimize the complexity of the input signal while maximizing the responsiveness of the tracking vehicle by creating detailed mathematical representations that allow for greatest flexibility in kinematic response.…”

Section: Introductionmentioning

confidence: 99%

“…Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations 1. Video link: https:// www.…”

mentioning

confidence: 99%

See 3 more Smart Citations

A Follow-the-Leader Strategy Using Hierarchical Deep Neural Networks with Grouped Convolutions

Solomon¹,

Charette

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

The task of following-the-leader is implemented using a hierarchical deep neural network (DNN) end-to-end driving model to match the direction and speed of a target pedestrian. The model uses a classifier DNN to determine if the pedestrian is within the field of view of the camera sensor. If the pedestrian is present, the image stream from the camera is fed to a regression DNN which simultaneously adjusts the autonomous vehicle's steering and throttle to keep cadence with the pedestrian. If the pedestrian is not visible, the vehicle uses a straightforward exploratory search strategy to reacquire the tracking objective. The classifier and regression DNNs incorporate grouped convolutions to boost model performance as well as to significantly reduce parameter count and compute latency. The models are trained on the intelligence processing unit (IPU) to leverage its fine-grain compute capabilities to minimize time-to-train. The results indicate very robust tracking behavior on the part of the autonomous vehicle in terms of its steering and throttle profiles, while requiring minimal data collection to produce. The throughput in terms of processing training samples has been boosted by the use of the IPU in conjunction with grouped convolutions by a factor ∼ 3.5 for training of the classifier and a factor of ∼ 7 for the regression network. A recording of the vehicle tracking a pedestrian has been produced and is available on the web.

show abstract

Section: A Random Walkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations 1. Video link: https:// www.…”

mentioning

confidence: 99%

See 2 more Smart Citations

A Follow-the-Leader Strategy Using Hierarchical Deep Neural Networks with Grouped Convolutions

Solomon¹,

Charette

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

show abstract

“…In Baarath et al ( 24 ), the authors design a simple robot platooning system by developing a kinematic model of the robots and using a Proportional-Integral-Drivative (PID) controller to control their movement.The numerical simulations of the controller are verified by using a robot following a person. A similar approach is found in Besseghieur et al ( 17 ), which also creates a mathematical model of the robots used (TURTLEBOT) to deal with the platooning problem.…”

Section: Robotic Applications In Transport Researchmentioning

confidence: 99%

Robotic Competitions to Design Future Transport Systems: The Case of JRC AUTOTRAC 2020

Ciuffo

Makridis

Padovan

et al. 2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Vehicle automation and connectivity bring new opportunities for safe and sustainable mobility in urban and highway networks. Such opportunities are however not directly associated with traffic flow improvements. Research on exploitation of connected and automated vehicles (CAVs) toward a more efficient traffic currently remains at a theoretical level, and/or based on simulation models with limited reliability. Furthermore, testing CAVs in the real world is still costly and very challenging from an implementation perspective. A possible alternative is to use automated robots. By designing and testing both the low- and the high-level controllers of CAVs, it is indeed possible to reach a better understanding of the challenges that future vehicles will need to face. Robotic applications can effectively test these challenges within a wide variety of research communities—for example, via robotic competitions. Along this direction, the Joint Research Centre has organized the first European robotic traffic competition for automated miniature vehicles. Each team participated with four robots and was judged based on a set of indicators that assess the collective behaviors of the vehicles. Results show the suitability of the methodology with different teams proposing completely different approaches to deal with the challenge and thus achieving different results. Future competitions may further raise awareness about the possibility of using CAVs to improve traffic and to engage with a broader community to design systems that are really capable of achieving this goal.

show abstract

An intelligent highway traffic model using cooperative vehicle platooning techniques

Rakkesh

Weerasinghe

Ranasinghe

2017

2017 Moratuwa Engineering Research Conference (MERCon)

View full text Add to dashboard Cite

Platooning strategy of mobile robot: simulation and experiment

Cited by 3 publications

References 14 publications

A Follow-the-Leader Strategy Using Hierarchical Deep Neural Networks with Grouped Convolutions

A Follow-the-Leader Strategy Using Hierarchical Deep Neural Networks with Grouped Convolutions

Robotic Competitions to Design Future Transport Systems: The Case of JRC AUTOTRAC 2020

An intelligent highway traffic model using cooperative vehicle platooning techniques

Contact Info

Product

Resources

About