Probabilistic pointing target prediction via inverse optimal control

Ziebart, Brian D.; Dey, Anind K.; Bagnell, J. Andrew

doi:10.1145/2166966.2166968

Cited by 82 publications

(59 citation statements)

References 24 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, [63] presents an approach to pointing target prediction that internally uses an inverse optimal control algorithm. This determines a cost function for which the human pointing trajectory would be optimal, and this approach could potentially be integrated with the above mentioned optimal control models.…”

Section: Dynamic Modelsmentioning

confidence: 99%

Control Theoretic Models of Pointing

Müller

Oulasvirta

Murray-Smith

2017

ACM Trans. Comput.-Hum. Interact.

View full text Add to dashboard Cite

This article presents an empirical comparison of four models from manual control theory on their ability to model targeting behaviour by human users using a mouse: McRuer's Crossover, Costello's Surge, secondorder lag (2OL), and the Bang-bang model. Such dynamic models are generative, estimating not only movement time, but also pointer position, velocity, and acceleration on a moment-to-moment basis. We describe an experimental framework for acquiring pointing actions and automatically fitting the parameters of mathematical models to the empirical data. We present the use of time-series, phase space, and Hooke plot visualisations of the experimental data, to gain insight into human pointing dynamics. We find that the identified control models can generate a range of dynamic behaviours that captures aspects of human pointing behaviour to varying degrees. Conditions with a low index of difficulty (ID) showed poorer fit because their unconstrained nature leads naturally to more behavioural variability. We report on characteristics of human surge behaviour (the initial, ballistic sub-movement) in pointing, as well as differences in a number of controller performance measures, including overshoot, settling time, peak time, and rise time. We describe trade-offs among the models. We conclude that control theory offers a promising complement to Fitts' law based approaches in HCI, with models providing representations and predictions of human pointing dynamics, which can improve our understanding of pointing and inform design.

show abstract

Section: Dynamic Modelsmentioning

confidence: 99%

Control Theoretic Models of Pointing

Müller

Oulasvirta

Murray-Smith

2017

ACM Trans. Comput.-Hum. Interact.

View full text Add to dashboard Cite

show abstract

“…Lank and colleagues also employed motion kinematics where they assume Downloaded by [University of Nebraska, Lincoln] at 00:16 10 April 2015 minimum jerk law for pointing motion and fit a quadratic function to partial trajectory to predict endpoint (Lank, Chen, & Ruiz, 2007;Ruiz & Lank, 2010). Ziebart, Dey, and Bagnell (2012) used inverse optimal control equations to predict target and compared its performance with other polynomial equations modeling cursor trajectory. Pasqual and Wobbrock (2014) proposed a new approach based on creating a library of velocity profiles and matching the instantaneous velocity to a predefined template.…”

Section: Target Prediction Modelmentioning

confidence: 99%

Multimodal Intelligent Eye-Gaze Tracking System

Biswas

Langdon

2015

International Journal of Human-Computer Interaction

View full text Add to dashboard Cite

This article presents a series of user studies to develop a new eye-gaze tracking-based pointing system. We developed a new target prediction model that works for different input modalities and combined the eye-gaze tracking-based pointing with a joystick controller that can reduce pointing and selection times. The system finds important applications in cockpit of combat aircraft and for computer novice users. User studies confirmed that users can perform significantly faster using this new eye-gaze tracking-based system for both military and everyday computing tasks compared to existing input devices. As part of the study it was also found that the amplitude of maximum power component obtained through Fourier Transform of pupil signal significantly correlates with selection times and perceived cognitive load of users in terms of Task Load Index scores.

show abstract

“…Unfortunately, when sub-optimal behavior is demonstrated 5 The continuous state and control setting has been investigated [62] and applied to predicting computer cursor pointing targets from partial motion trajectories [64]. 6 We consider finite horizons, T , in this work, but infinite horizons can also be considered by requiring the decision process to terminate with some probability after each time step, i.e., a discount factor, or that some states are absorbing to make the total reward received finite.…”

Section: A Backgroundmentioning

confidence: 99%

The Principle of Maximum Causal Entropy for Estimating Interacting Processes

Ziebart

Bagnell

Dey

2013

IEEE Trans. Inform. Theory

Self Cite

115

119

View full text Add to dashboard Cite

Abstract-The principle of maximum entropy provides a powerful framework for estimating joint, conditional, and marginal probability distributions. However, there are many important distributions with elements of interaction and feedback where its applicability has not been established. This work presents the principle of maximum causal entropy-an approach based on directed information theory for estimating an unknown process based on its interactions with a known process. We demonstrate the breadth of the approach using two applications: a predictive solution for inverse optimal control in decision processes and computing equilibrium strategies in sequential games.

show abstract

Probabilistic pointing target prediction via inverse optimal control

Cited by 82 publications

References 24 publications

Control Theoretic Models of Pointing

Control Theoretic Models of Pointing

Multimodal Intelligent Eye-Gaze Tracking System

The Principle of Maximum Causal Entropy for Estimating Interacting Processes

Contact Info

Product

Resources

About