End-to-End Automated Guided Modular Vehicle

Curiel-Ramirez, Luis A.; Ramírez-Mendoza, Ricardo A.; Bautista-Montesano, Rolando; Bustamante-Bello, Rogelio; González-Hernández, Hugo G.; Reyes-Avedaño, Jorge A.; Gallardo-Medina, Edgar Cortes

doi:10.3390/app10124400

Cited by 18 publications

(10 citation statements)

References 42 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [24] introduce a cooperative ACC method that makes use of an ACC controller created using the concept of RL in order to manage traffic efficiency and safety, showing impressive results in their experiments with a low-level controller. The work in [25] successfully implemented a method for Society of Automotive Engineers (SAE) low-cost modular AV by designing a vehicle unique in the industry, and which proves to be able to transport persons successfully. The approach in this work leads to the realistic application of behavioral replication and imitation learning algorithms in a stable context.…”

Section: Related Workmentioning

confidence: 99%

Increasing the Safety of Adaptive Cruise Control Using Physics-Guided Reinforcement Learning

et al. 2021

View full text Add to dashboard Cite

This paper presents a novel approach for improving the safety of vehicles equipped with Adaptive Cruise Control (ACC) by making use of Machine Learning (ML) and physical knowledge. More exactly, we train a Soft Actor-Critic (SAC) Reinforcement Learning (RL) algorithm that makes use of physical knowledge such as the jam-avoiding distance in order to automatically adjust the ideal longitudinal distance between the ego- and leading-vehicle, resulting in a safer solution. In our use case, the experimental results indicate that the physics-guided (PG) RL approach is better at avoiding collisions at any selected deceleration level and any fleet size when compared to a pure RL approach, proving that a physics-informed ML approach is more reliable when developing safe and efficient Artificial Intelligence (AI) components in autonomous vehicles (AVs).

show abstract

Section: Related Workmentioning

confidence: 99%

Increasing the Safety of Adaptive Cruise Control Using Physics-Guided Reinforcement Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Then, the network learns the response of the driver to obstacles in other locations. According to [61], a whole model can be trained using only raw data and expect to have a steering output. This approach is called end-to-end learning, but electromobility and autonomous driving named BC are much more appealing.…”

Section: Behavioral Cloning (Bc)mentioning

confidence: 99%

Object Detection, Distributed Cloud Computing and Parallelization Techniques for Autonomous Driving Systems

et al. 2021

View full text Add to dashboard Cite

Autonomous vehicles are increasingly becoming a necessary trend towards building the smart cities of the future. Numerous proposals have been presented in recent years to tackle particular aspects of the working pipeline towards creating a functional end-to-end system, such as object detection, tracking, path planning, sentiment or intent detection, amongst others. Nevertheless, few efforts have been made to systematically compile all of these systems into a single proposal that also considers the real challenges these systems will have on the road, such as real-time computation, hardware capabilities, etc. This paper reviews the latest techniques towards creating our own end-to-end autonomous vehicle system, considering the state-of-the-art methods on object detection, and the possible incorporation of distributed systems and parallelization to deploy these methods. Our findings show that while techniques such as convolutional neural networks, recurrent neural networks, and long short-term memory can effectively handle the initial detection and path planning tasks, more efforts are required to implement cloud computing to reduce the computational time that these methods demand. Additionally, we have mapped different strategies to handle the parallelization task, both within and between the networks.

show abstract

“…Package 3 should be delivered before package 1 because 1.1 is smaller than 1.2. us, the IDs of packages delivered by robot 1 are elements [3,1], and they are delivered following this order. Similarly, robot 2 is in charge of delivering elements [4,2,5] with the corresponding order.…”

Section: Problem Formulation Considering Multiplementioning

confidence: 99%

“…Unmanned ground vehicles (UGVs) have been successfully applied in diverse applications, such as planet exploration on the Moon and Mars [1,2]. In recent years, UGVs have also been used for logistic services to reduce delivery costs [3].…”

Section: Introductionmentioning

confidence: 99%

Autonomous Last-Mile Delivery Based on the Cooperation of Multiple Heterogeneous Unmanned Ground Vehicles

Ding

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

With the development of e-commerce, the last-mile delivery has become a significant part of customers’ shopping experience. In this paper, an autonomous last-mile delivery method using multiple unmanned ground vehicles is investigated. Being a smart logistics service, it provides a promising solution to reduce the delivery cost, improve efficiency, and avoid the spread of airborne diseases, such as SARS and COVID-19. By using a cooperation strategy with multiple heterogeneous robots, contactless parcel delivery can be carried out within apartment complexes efficiently. In this paper, the last-mile delivery with heterogeneous UGVs is formulated as an optimization problem aimed at minimizing the maximum makespan to complete all tasks. Then, a heuristic algorithm combining the Floyd’s algorithm and PSO algorithm is proposed for task assignment and path planning. This algorithm is further realized in a distributed scheme, with all robots in a swarm working together to obtain the best task schedule. A good solution with an optimized makespan is achieved by considering the constraints of various robots in terms of speed and payload. Simulations and experiments are carried out and the obtained results confirm the validity and applicability of the developed approaches.

show abstract

End-to-End Automated Guided Modular Vehicle

Cited by 18 publications

References 42 publications

Increasing the Safety of Adaptive Cruise Control Using Physics-Guided Reinforcement Learning

Increasing the Safety of Adaptive Cruise Control Using Physics-Guided Reinforcement Learning

Object Detection, Distributed Cloud Computing and Parallelization Techniques for Autonomous Driving Systems

Autonomous Last-Mile Delivery Based on the Cooperation of Multiple Heterogeneous Unmanned Ground Vehicles

Contact Info

Product

Resources

About