scispace - formally typeset

Conference

International Conference on Ubiquitous Robots and Ambient Intelligence 

About: International Conference on Ubiquitous Robots and Ambient Intelligence is an academic conference. The conference publishes majorly in the area(s): Robot & Mobile robot. Over the lifetime, 1669 publication(s) have been published by the conference receiving 5431 citation(s).


Papers
More filters
Proceedings ArticleDOI
17 Dec 2015
TL;DR: A new way to model, train and recognize different activities using advanced HMM is proposed, resulting up to the mean recognition of 57.69% over the state of the art methods using IM-DailyDepthActivity dataset.
Abstract: In this paper, a depth camera-based novel approach for human activity recognition is presented using robust depth silhouettes context features and advanced Hidden Markov Models (HMMs). During HAR framework, at first, depth maps are processed to identify human silhouettes from noisy background by considering frame differentiation constraints of human body motion and compute depth silhouette area for each activity to track human movements in a scene. From the depth silhouettes context features, temporal frames information are computed for intensity differentiation measurements, depth history features are used to store gradient orientation change in overall activity sequence and motion difference features are extracted for regional motion identification. Then, these features are processed by Principal component analysis for dimension reduction and k-mean clustering for code generation to make better activity representation. Finally, we proposed a new way to model, train and recognize different activities using advanced HMM. Experimental results show superior recognition rate, resulting up to the mean recognition of 57.69% over the state of the art methods using IM-DailyDepthActivity dataset. In addition, MSRAction3D dataset also showed some promising results.

54 citations

Proceedings ArticleDOI
01 Nov 2011
TL;DR: To implement this work, Cortex-A8 series S5PV210 embedded processor and Android operating system are correlated and the robot has an autonomous and manual travel and is controlled by only smart phone.
Abstract: In this work, Android operating system based robot platform and smart phone operated control and monitoring system are introduced. To implement this work, Cortex-A8 series S5PV210 embedded processor and Android operating system are correlated. The robot has an autonomous and manual travel and is controlled by only smart phone. In the Android OS (Operating System), the camera image is compressed to JPEG format and the image file is delivered to a smart phone through 802.11x wireless LAN communication which utilizes TCP/IP communication socket programming. Later, the transferred image data are converted into BMP format, which enables a real time image display.

49 citations

Proceedings ArticleDOI
26 Jun 2018
TL;DR: Deep Reinforcement Learning autonomous navigation and obstacle avoidance of self-driving cars, applied with Deep Q Network to a simulated car an urban environment using two types of sensor data as input: camera sensor and laser sensor in front of the car.
Abstract: Deep Reinforcement Learning has led us to newer possibilities in solving complex control and navigation related tasks. The paper presents Deep Reinforcement Learning autonomous navigation and obstacle avoidance of self-driving cars, applied with Deep Q Network to a simulated car an urban environment. The approach uses two types of sensor data as input: camera sensor and laser sensor in front of the car. It also designs a cost-efficient high-speed car prototype capable of running the same algorithm in real-time. The design uses a camera and a Hokuyo Lidar sensor in the car front. It uses embedded GPU (Nvidia-TX2) for running deep-learning algorithms based on sensor inputs.

46 citations

Proceedings ArticleDOI
17 Dec 2015
TL;DR: A video-based novel approach for human activity recognition is presented using robust hybrid features and embedded Hidden Markov Models to explore gradient orientation change, intensity differentiation, temporal variation and local motion of specific body parts.
Abstract: Activity and action detection, tracking and recognition are very demanding research area in computer vision and human computer interaction. In this paper, a video-based novel approach for human activity recognition is presented using robust hybrid features and embedded Hidden Markov Models. In the proposed HAR framework, depth maps are analyzed by temporal motion identification method to segment human silhouettes from noisy background and compute depth silhouette area for each activity to track human movements in a scene. Several representative features, including invariant, depth sequential silhouettes and spatiotemporal body joints features were fused together to explore gradient orientation change, intensity differentiation, temporal variation and local motion of specific body parts. Then, these features are processed by the dynamics of their respective class and learned, trained and recognized with specific embedded HMM having active feature values. Our experiments on two depth datasets demonstrate that the proposed features are efficient and robust over the state of the arts features for human activity recognition especially when there are similar postures of different activities.

43 citations

Proceedings ArticleDOI
01 Jun 2017
TL;DR: From the literature, some most interested issues such as potential applications, representation of multiple quadrotor formation, consensus, formation control, formation configurations, localization, etc are summarized.
Abstract: In this paper, we try to show the state of the art on the formation control of multiple quadrotors. From the literature, we summarize some most interested issues such as potential applications, representation of multiple quadrotor formation, consensus, formation control, formation configurations, localization, etc. According to these research, we point out the difficulties and the tendency of research in the field of multiple quadrotors control.

40 citations

Network Information
Related Conferences (5)
Intelligent Robots and Systems

20.2K papers, 442.7K citations

87% related
International Conference on Advanced Intelligent Mechatronics

4.8K papers, 35.9K citations

87% related
International Conference on Robotics and Automation

34.2K papers, 1.1M citations

86% related
Robotics and Biomimetics

6.2K papers, 37.6K citations

86% related
IEEE-RAS International Conference on Humanoid Robots

2K papers, 40.5K citations

82% related
Performance
Metrics
No. of papers from the Conference in previous years
YearPapers
201999
2018127
2017251
2016225
2015170
2014172