The VILMA intelligent vehicle: an architectural design for cooperative control between driver and automated system

Garcia-Bedoya, Olmer; Vitor, Giovani Bernardes; Ferreira, Janito Vaqueiro; Meirelles, Pablo Siqueira; Neto, Arthur de Miranda

doi:10.1007/s40534-018-0160-3

Cited by 6 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Information and communication technology (ICT) continues to find applications in transportation to reduce collisions, reduce pollution, ameliorate mobility issues, modernize public transportation, and share resources, materials and space [12]. According to a study, there are 1.3 million deaths globally every year due to drunk, drugged, distracted, or drowsy driving [34]. Autonomous AI systems that can save lives by eliminating these human follies offer the following advantages that motivate research in self-driving cars:…”

Section: Advantages Of Self-driving Carsmentioning

confidence: 99%

“…• Reduced accidents are expected to be beneficial for children and the elderly, encouraging people to feel comfortable and amiable towards self-driving cars [34].…”

Section: Advantages Of Self-driving Carsmentioning

confidence: 99%

“…• Self-driving electric cars would introduce a greener mode of transport, leading to less greenhouse and noise pollution, along with increased mobility for the elderly and disabled people [34].…”

Section: Advantages Of Self-driving Carsmentioning

confidence: 99%

“…• The acceptance of self-driving technology at philosophical, ethical and technological levels is a fundamental research problem in psychology and cognitive science. It is argued that in case autonomous vehicles and AI systems malfunction, a person would not die or suffer injuries if they themselves were in control of the system [34].…”

Section: Probable Disadvantages and Drawbacks Of Self-driving Carsmentioning

confidence: 99%

See 3 more Smart Citations

Safe Driving Of Autonomous Vehicles Through Improved Deep Reinforcement Learning

Gupta¹

2021

Preprint

View full text Add to dashboard Cite

In this thesis, we propose an environment perception framework for autonomous driving using deep reinforcement learning (DRL) that exhibits learning in autonomous vehicles under complex interactions with the environment, without being explicitly trained on driving datasets. Unlike existing techniques, our proposed technique takes the learning loss into account under deterministic as well as stochastic policy gradient. We apply DRL to object detection and safe navigation while enhancing a self-driving vehicle’s ability to discern meaningful information from surrounding data. For efficient environmental perception and object detection, various Q-learning based methods have been proposed in the literature. Unlike other works, this thesis proposes a collaborative deterministic as well as stochastic policy gradient based on DRL. Our technique is a combination of variational autoencoder (VAE), deep deterministic policy gradient (DDPG), and soft actor-critic (SAC) that adequately trains a self-driving vehicle. In this work, we focus on uninterrupted and reasonably safe autonomous driving without colliding with an obstacle or steering off the track. We propose a collaborative framework that utilizes best features of VAE, DDPG, and SAC and models autonomous driving as partly stochastic and partly deterministic policy gradient problem in continuous action space, and continuous state space. To ensure that the vehicle traverses the road over a considerable period of time, we employ a reward-penalty based system where a higher negative penalty is associated with an unfavourable action and a comparatively lower positive reward is awarded for favourable actions. We also examine the variations in policy loss, value loss, reward function, and cumulative reward for ‘VAE+DDPG’ and ‘VAE+SAC’ over the learning process.

show abstract

Section: Advantages Of Self-driving Carsmentioning

confidence: 99%

“…• Reduced accidents are expected to be beneficial for children and the elderly, encouraging people to feel comfortable and amiable towards self-driving cars [34].…”

Section: Advantages Of Self-driving Carsmentioning

confidence: 99%

Section: Advantages Of Self-driving Carsmentioning

confidence: 99%

Section: Probable Disadvantages and Drawbacks Of Self-driving Carsmentioning

confidence: 99%

See 2 more Smart Citations

Safe Driving Of Autonomous Vehicles Through Improved Deep Reinforcement Learning

Gupta¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The autonomous robotic vehicle, was designed over the concept of layers and functional groups taking account that, this type of architecture facilitates the separation of functions and development, allowing for the definition of interfaces between the various subsystems [5] [6]. Below is described the software architecture and hardware for the development of VILMA01 [7] in response to questions of the layers in the autonomous vehicle.…”

Section: System Architecturementioning

confidence: 99%

Sensor Fusion Tests for an Autonomous Vehicle, using Extended Kalman Filter

O.¹,

V²

2018

JESTR

View full text Add to dashboard Cite

Intelligent and autonomous vehicle concepts have received a great degree of attention in recent years. In addition to a set of sensors, actuators, mechanism, and components (hardware and/or software), new technologies should be developed in support of Automation, Control, Perception, Localization, and Navigation. This article presents the initial tests with the instrumentation of an autonomous vehicle. The design was implemented making the automation of a Fiat Punto vehicle. The aim of this instrumentation is to increase the safety of the car through a sensor fusion localization using Extended Kalman Filter. This article presents the experimental result of applying this sensor fusion technique over the sensors installed actually on the vehicle. Some conclusions and future improvement over the system are proposed.

show abstract

GPU-Implementation of a Sequential Monte Carlo Technique for the Localization of an Ackerman Robot

Garcia-Bedoya

Acosta

Díaz

2018

Communications in Computer and Information Science

View full text Add to dashboard Cite

The VILMA intelligent vehicle: an architectural design for cooperative control between driver and automated system

Cited by 6 publications

References 23 publications

Safe Driving Of Autonomous Vehicles Through Improved Deep Reinforcement Learning

Safe Driving Of Autonomous Vehicles Through Improved Deep Reinforcement Learning

Sensor Fusion Tests for an Autonomous Vehicle, using Extended Kalman Filter

GPU-Implementation of a Sequential Monte Carlo Technique for the Localization of an Ackerman Robot

Contact Info

Product

Resources

About