Human-in-the-Loop: Terminal constraint receding horizon control with human inputs

Chipalkatty, Rahul; Egerstedt, Magnus

doi:10.1109/robot.2010.5509715

Cited by 15 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and the task is modeled by the constraint, x(k + N ) ∈ X f = {x | M x = b}, one can solve P MP C analytically as long as the human input sequences are sufficiently regular. In particular, if the human input sequences belong to the Hilbert space of square-summable sequences 3 (denoted by H), in [19], P MP C was solved as a direct application of Hilbert's Projection Theorem, following the procedure in [27]. In particular, the optimal u opt k at time k is given by…”

Section: Solving the Mpcmentioning

confidence: 99%

“…In this paper, we frame the mixed initiative interaction problem as a model predictive control problem, following the initial work in [19]. The proposed approach makes a distinction between low-level (automatic controller) tasks and high-level (human) tasks, with completion guarantees associated with the low-level tasks without the need for strong assumptions on the human input signals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Less Is More: Mixed-Initiative Model-Predictive Control With Human Inputs

2013

Self Cite

View full text Add to dashboard Cite

This paper presents a new method for injecting human inputs in mixed initiative interactions between humans and robots. The method is based on a model predictive control (MPC) formulation, which inevitably involves predicting the system (robot dynamics as well as human inputs) into the future. These predictions are complicated by the fact that the human is interacting with the robot, causing the prediction method itself to have an effect on future human inputs. We investigate and develop different prediction schemes, including fixed and variable horizon MPCs and human input estimators of different orders. Through a search-and-rescue-inspired human operator study, we arrive at the conclusion that the simplest prediction methods outperform the more complex ones, i.e., in this particular case, less is indeed more.Index Terms-human-robot interaction, model-predictive control, mixed initiative initeractions.

show abstract

Section: Solving the Mpcmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Less Is More: Mixed-Initiative Model-Predictive Control With Human Inputs

2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [11], based on the objective of minimizing the human effort, a role adaptation strategy is developed to switch between model-based and model-free predictions in the case of partially known tasks. In [12], [13], the terminal constraint receding horizon control is developed for shared control of human and robot, such that the common goal can be achieved subsequently. A homotopy switching model is developed in [14] for dyad haptic interaction in physical collaborative tasks.…”

Section: Introductionmentioning

confidence: 99%

Shared control of human and robot by approximate dynamic programming

Tee

Yan

et al. 2015

2015 American Control Conference (ACC)

View full text Add to dashboard Cite

Abstract-This paper aims at proposing a general framework of human-robot shared control for a natural and effective interface. A typical human-robot collaboration scenario is investigated, and a framework of shared control is developed based on finding the solution to an optimization problem. Human dynamics are taken into account in the analysis of the coupled human-robot system, and objectives of both human and robot are considered. Approximate dynamic programming is employed to solve the optimization problem in the presence of unknown human and robot dynamics. The validity of the proposed method is verified through simulation studies.

show abstract

“…This paradigm has been successfully applied to obtain skills such as ball manipulation [20] with an anthropomorphic robot hand, and balanced inverse kinematics for a humanoid robot [22], and more recently tasks that involve force based policies [21], [25]. It will be fair to say that robotic researchers are becoming increasingly more interested in human-in-the-loop robot control and learning, which provides a platform for both human and robot to learn actively [25][26][27][28].…”

Section: Introductionmentioning

confidence: 99%

Simultaneous human-robot adaptation for effective skill transfer

Zamani

Öztop

2015

2015 International Conference on Advanced Robotics (ICAR)

View full text Add to dashboard Cite

Due to copyright restrictions, the access to the full text of this article is only available via subscription.In this paper, we propose and implement a human-in-the loop robot skill synthesis framework that involves simultaneous adaptation of the human and the robot. In this framework, the human demonstrator learns to control the robot in real-time to make it perform a given task. At the same time, the robot learns from the human guided control creating a non-trivial coupled dynamical system. The research question we address is how this system can be tuned to facilitate faster skill transfer or improve the performance level of the transferred skill. In the current paper we report our initial work for the latter. At the beginning of the skill transfer session, the human demonstrator controls the robot exclusively as in teleoperation. As the task performance improves the robot takes increasingly more share in control, eventually reaching full autonomy. The proposed framework is implemented and shown to work on a physical cart-pole setup. To assess whether simultaneous learning has advantage over the standard sequential learning (where the robot learns from the human observation but does not interfere with the control) experiments with two groups of subjects were performed. The results indicate that the final autonomous controller obtained via simultaneous learning has a higher performance measured as the average deviation from the upright posture of the pole.European Commissio

show abstract

Human-in-the-Loop: Terminal constraint receding horizon control with human inputs

Cited by 15 publications

References 13 publications

Less Is More: Mixed-Initiative Model-Predictive Control With Human Inputs

Less Is More: Mixed-Initiative Model-Predictive Control With Human Inputs

Shared control of human and robot by approximate dynamic programming

Simultaneous human-robot adaptation for effective skill transfer

Contact Info

Product

Resources

About