A recurrent neural network approach to virtual environment latency reduction

Garrett, Aaron; Aguilar, Mario; Barniv, Yair

doi:10.1109/ijcnn.2002.1007498

Cited by 12 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although dead reckoning works well for gaming applications, its main purpose it to reduce network traffic and has not been proven to work for more complex human movement patterns. Other predictive techniques have been studied for use in virtual reality, but no consensus has been made as the most appropriate method [8].…”

Section: Introductionmentioning

confidence: 99%

Towards Modeling Human Arm Movement in a CVE

Stakem

AlRegib

Juang

2007

Proceedings of the ImmersCom

View full text Add to dashboard Cite

Although Collaborative Virtual Environments share many characteristics in common with first person 3D games, CVEs strive for a deeper level of immersion by networking together individuals with more natural input devices. More complex input devices such as data gloves and positional trackers have additional processing delay and when compounded with network delay can cause CVE applications to lag and become jerky. The purpose of this experiment was to measure and model typical movements from users utilizing data gloves and positional trackers so that algorithms can be designed to help combat the inherent delay and jitter in a CVE. Most movements studied were shown to have a rough Gaussian shaped speed profile, but intricate manipulative movements exhibited greater peaks and valleys than typical reaching movement.

show abstract

Section: Introductionmentioning

confidence: 99%

Towards Modeling Human Arm Movement in a CVE

Stakem

AlRegib

Juang

2007

Proceedings of the ImmersCom

View full text Add to dashboard Cite

show abstract

“…Required is that the error in predicted angular acceleration is small enough such that it can be neglected. In [10][11][12][13] several methods to predict angular acceleration have been proposed. These methods are, however, rather complex, varying from multiple neural networks to extensive Kalman filtering.…”

Section: Predictionmentioning

confidence: 99%

Robust Flight Control Using Incremental Nonlinear Dynamic Inversion and Angular Acceleration Prediction

Sieberling

Chu

Mulder

2010

Journal of Guidance, Control, and Dynamics

365

268

View full text Add to dashboard Cite

This paper presents a flight control strategy based on nonlinear dynamic inversion. The approach presented, called incremental nonlinear dynamic inversion, uses properties of general mechanical systems and nonlinear dynamic inversion by feeding back angular accelerations. Theoretically, feedback of angular accelerations eliminates sensitivity to model mismatch, greatly increasing the robust performance of the system compared with conventional nonlinear dynamic inversion. However, angular accelerations are not readily available. Furthermore, it is shown that angular acceleration feedback is sensitive to sensor measurement time delays. Therefore, a linear predictive filter is proposed that predicts the angular accelerations, solving the time delay and angular acceleration availability problem. The predictive filter uses only references and measurements of angular rates. Hence, the proposed control method makes incremental nonlinear dynamic inversion practically available using conventional inertial measurement units.

show abstract

“…Prediction based techniques have been used to feed back predicted movements of head (Akatsuka and Bekey, 1998;Garrett et al, 2002), ownership requirements (Roberts and Sharkey, 1997), and forces (Kim et al, 2004) to users before final results are available. HCI based techniques show some system information to users through predictive display (Burkert et al, 2004;Noyes and Sheridan, 1984) and user interface widgets such as delay gauge, area of uncertainty, past shadow, and ghost ball etc.…”

Section: Site0mentioning

confidence: 99%

An HCI method to improve the human performance reduced by local-lag mechanism

Chen

Hong

et al. 2007

Interacting with Computers

View full text Add to dashboard Cite

Local-lag mechanism can maintain consistency for replicated continuous applications, but with a tradeoff of adding delay to local operations. To relieve the negative effects of the delay, this paper proposes an HCI method named echo. With the help of the echo method users can immediately perceive the results of their operations and how large the lag is. In order to evaluate the proposed method, a desktop collaborative virtual environment (CVE) system and a virtual object control task were employed to study the effects of the echo method on human performance (including task completion time, error count, and interaction quality). Experimental results indicate that when the lag exceeds 100 ms the echo method can improve human performance with the effects becoming more evident when a larger lag is used.

show abstract

A recurrent neural network approach to virtual environment latency reduction

Cited by 12 publications

References 7 publications

Towards Modeling Human Arm Movement in a CVE

Towards Modeling Human Arm Movement in a CVE

Robust Flight Control Using Incremental Nonlinear Dynamic Inversion and Angular Acceleration Prediction

An HCI method to improve the human performance reduced by local-lag mechanism

Contact Info

Product

Resources

About