Driving Assistant Companion With Voice Interface Using Long Short-Term Memory Networks

Park, Jehyun; Son, Hojoon; Lee, Jisuk; Choi, Jongeun

doi:10.1109/tii.2018.2861739

Cited by 28 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar scheme is proposed by authors in [22], where they use a voice-assistant along with a camera system for fall detection in a smarthome environment. Similar such works have been done by other authors in [23][24][25] for improving the various technical aspects relevant in voice-based systems.…”

Section: Current State-of-art Of Voice-assistantssupporting

confidence: 57%

Usability Evaluation of Artificial Intelligence-Based Voice Assistants: The Case of Amazon Alexa

2021

View full text Add to dashboard Cite

Section: Current State-of-art Of Voice-assistantssupporting

confidence: 57%

Usability Evaluation of Artificial Intelligence-Based Voice Assistants: The Case of Amazon Alexa

2021

View full text Add to dashboard Cite

“…As previously noted, current IPA technology incorporates Machine Learning techniques (deep learning and reinforcement learning) resources based on voice-recognition systems [36]. IPAs provide users with information on coursework, facilitating its planning [37,38]. Specifically, the recent use of this technology in university-learning contexts has been associated with very good results and levels of acceptance, specifically among students with special educational needs (visual, auditory, memory, etc.)…”

Section: The Use Of Voice Assistants: Applicability In Prevention Of mentioning

confidence: 99%

Effectiveness of Using Voice Assistants in Learning: A Study at the Time of COVID-19

Manzanares

Sánchez

Ochoa-Orihuel

2020

IJERPH

View full text Add to dashboard Cite

The use of advanced learning technologies in a learning management system (LMS) can greatly assist learning processes, especially when used in university environments, as they promote the development of Self-Regulated learning, which increases academic performance and student satisfaction towards personal learning. One of the most innovative resources that an LMS may have is an Intelligent Personal Assistant (IPA). We worked with a sample of 109 third-grade students following Health Sciences degrees. The aims were: (1) to verify whether there will be significant differences in student access to the LMS, depending on use versus non-use of an IPA. (2) To verify whether there will be significant differences in student learning outcomes depending on use versus non-use of an IPA. (3) To verify whether there will be significant differences for student satisfaction with teaching during the COVID-19 pandemic, depending on use versus non-use of an IPA. (4) To analyze student perceptions of the usefulness of an IPA in the LMS. We found greater functionality in access to the LMS and satisfaction with teaching, especially during the health crisis, in the group of students who had used an IPA. However, both the expansion of available information and the usability of the features embedded in an IPA are still challenging issues.

show abstract

“…Besides, there are still many Advanced Driver Assistance Systems (ADAS) like the pedestrian detection [8], autonomous parking systems and Tesla's Autopilot. In [9], a driving assistant companion system that provides drivers with useful information using an LSTM network is proposed. In [10], they propose a mixed-integer linear program-based urban traffic management scheme for an all connected vehicle environment at an intersection scenario.…”

Section: B Related Workmentioning

confidence: 99%

“…Using this model, we can approximate the injury severity score in our simulated environment by observing the speed change between before and after the crash and the area of most significant damage. The reward function is defined in (9),…”

Section: ) Goal-unaware Agentmentioning

confidence: 99%

Unexpected Collision Avoidance Driving Strategy Using Deep Reinforcement Learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

In this paper, we generated intelligent self-driving policies that minimize the injury severity in unexpected traffic signal violation scenarios at an intersection using the deep reinforcement learning. We provided guidance on reward engineering in terms of the multiplicity of objective function. We used a deep deterministic policy gradient method in the simulated environment to train self-driving agents. We designed two agents, one with a single-objective reward function of collision avoidance and the other with a multi-objective reward function of both collision avoidance and goal-approaching. We evaluated their performances by comparing the percentages of collision avoidance and the average injury severity against those of human drivers and an autonomous emergency braking (AEB) system. The percentage of collision avoidance of our agents were 78.89% higher than human drivers and 84.70% higher than the AEB system. The average injury severity score of our agents were only 8.92% of human drivers and 6.25% of the AEB system.

show abstract

Driving Assistant Companion With Voice Interface Using Long Short-Term Memory Networks

Cited by 28 publications

References 21 publications

Usability Evaluation of Artificial Intelligence-Based Voice Assistants: The Case of Amazon Alexa

Usability Evaluation of Artificial Intelligence-Based Voice Assistants: The Case of Amazon Alexa

Effectiveness of Using Voice Assistants in Learning: A Study at the Time of COVID-19

Unexpected Collision Avoidance Driving Strategy Using Deep Reinforcement Learning

Contact Info

Product

Resources

About