Parametric primitives for motor representation and control

Rauniyar, Amit; Matarić, Maja J.

doi:10.1109/robot.2002.1013465

Cited by 14 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…generates actions, can be introduced. In general, such a description is referred to as a controller, but is also known as a plan [53, p.560], behavior mapping [5,27,68,71], motor primitive [3], control policy [4] or inverse model [39]. Several important differences between these terms do exist, for example in terms of abstraction level and temporal extension, but for now they can all be said to implement the function π:…”

Section: Sensing and Actingmentioning

confidence: 99%

A Formalism for Learning from Demonstration^*

Billing

Hellström

2010

Paladyn, Journal of Behavioral Robotics

View full text Add to dashboard Cite

The paper describes and formalizes the concepts and assumptions involved in Learning from Demonstration (LFD), a common learning technique used in robotics. LFD-related concepts like goal, generalization, and repetition are here defined, analyzed, and put into context. Robot behaviors are described in terms of trajectories through information spaces and learning is formulated as mappings between some of these spaces. Finally, behavior primitives are introduced as one example of good bias in learning, dividing the learning process into the three stages of behavior segmentation, behavior recognition, and behavior coordination. The formalism is exemplified through a sequence learning task where a robot equipped with a gripper arm is to move objects to specific areas. The introduced concepts are illustrated with special focus on how bias of various kinds can be used to enable learning from a single demonstration, and how ambiguities in demonstrations can be identified and handled.

show abstract

Section: Sensing and Actingmentioning

confidence: 99%

A Formalism for Learning from Demonstration^*

Billing

Hellström

2010

Paladyn, Journal of Behavioral Robotics

View full text Add to dashboard Cite

show abstract

“…(22) and (23) requires a numerical search procedure, similar to thrust-inflow iterations seen in full-scale helicopter models. 47 However, a fortunate consequence of the trajectory interpolation algorithm is that only first-order equality constraint derivative information is required, requiring only implicit differentiation of the above relations.…”

Section: B Dynamic Feasibility and Boundary Conditionsmentioning

confidence: 99%

“…Recalling from Eqs. (22) and (23) that the initial trim pitch angle and input voltages vary withv i , insert the boundary parameter α into the corresponding rows of Eq. (24) to obtain…”

Section: Example: Bounded-control Quick-stop Maneuver Classmentioning

confidence: 99%

Nonlinear Trajectory Generation for Autonomous Vehicles via Parametrized Maneuver Classes

Dever

Mettler

Féron

et al. 2006

Journal of Guidance, Control, and Dynamics

View full text Add to dashboard Cite

A technique is presented for creating continuously parameterized classes of feasible system trajectories. These classes, which are useful for higher-level vehicle motion planners, follow directly from a small collection of userprovided example motions. A dynamically feasible trajectory interpolation algorithm generates a continuous family of vehicle maneuvers across a range of boundary conditions while enforcing nonlinear system equations of motion as well as nonlinear equality and inequality constraints. The scheme is particularly useful for describing motions that deviate widely from the range of linearized dynamics and where satisfactory example motions may be found from off-line nonlinear programming solutions or motion capture of human-piloted flight. The interpolation algorithm is computationally efficient, making it a viable method for real-time maneuver synthesis, particularly when used in concert with a vehicle motion planner. Experimental application to a three-degree-of-freedom rotorcraft test bed demonstrates the essential features of system and trajectory modeling, maneuver example selection, maneuver class synthesis, and integration into a hybrid system path planner. Nomenclature= goal-attainment binary variable b man = maneuver class binary variable C c, j = time duration constant for maneuver class j C s, j = time duration matrix for maneuver class j c i = vehicle model coefficientsmaneuver class duration state D x = differentiation operator with respect to variable x d i = vehicle model coefficients e = data matching error metric F = nonlinear equation set f = nonlinear program objective functioñ f = continuous-time dynamic consistency function g = inequality constraint vector H = planning decision horizon . ¶ Principal Member, Technical Staff, 555 Technology Square; mcconley@draper.com. h = equality constraint vector h bc = boundary condition equality constraint vector h 0 bc = boundary condition equality constraints invariant with α h em = dynamic consistency equality constraint vector h em = continuous-time dynamic consistency function i = summation index J = planning objective function J i = active constraint set i j = summation index k = spline order; planning decision step k i = affine maneuver design constants for planning l = summation index = linear constraint M c, j = state transition vector for maneuver class j M s, j = state transition matrix for maneuver class j M = vector of large numbers m j = binary variable for maneuver class j N = number of data samples N f = number of final condition maneuver parameters N i = number of initial condition maneuver parameters n v = number of spline coefficients for signal v p = finite-dimensional trajectory parametrization S e = sampling of unit interval for equality constraints S g = sampling of unit interval for inequality constraints s = arc length in v-space s i = ith sampling point T = maneuver duration T s = linear-time invariant (LTI)-mode discretization interval t = time u = direct difference vector u = projected feasible difference vector...

show abstract

“…the use of parametric primitives for motor representation by Mataric et. al [2] or parameterized movement primitives by Schaal, et. al [4].…”

Section: Related Workmentioning

confidence: 99%

Towards Robust Skill Learning With Prediction Guided Autonomy in Unknown Environments

Richert

Kleinjohann

Murmann

2006

2006 IEEE Mountain Workshop on Adaptive and Learning Systems

View full text Add to dashboard Cite

We present first steps towards an architecture that enables autonomous systems to learn and adapt basic behaviors to unknown environments. It can act as layer providing robust behaviors to higher-level layers like e.g. reinforcement learning or planning algorithms, that depend on encapsulated actions. With emphasis on robustness it is able to learn to control its actors without any information about the meaning of its actors. This is made possible by behavior modules that are learned together with their action-effect dependencies and their enabling preconditions by proactively carrying out experiments within their environment.

show abstract

Parametric primitives for motor representation and control

Abstract: Abstract

Cited by 14 publications

References 16 publications

A Formalism for Learning from Demonstration^*

A Formalism for Learning from Demonstration^*

Nonlinear Trajectory Generation for Autonomous Vehicles via Parametrized Maneuver Classes

Towards Robust Skill Learning With Prediction Guided Autonomy in Unknown Environments

Contact Info

Product

Resources

About

Parametric primitives for motor representation and control

Abstract: Abstract

Cited by 14 publications

References 16 publications

A Formalism for Learning from Demonstration*

A Formalism for Learning from Demonstration*

Nonlinear Trajectory Generation for Autonomous Vehicles via Parametrized Maneuver Classes

Towards Robust Skill Learning With Prediction Guided Autonomy in Unknown Environments

Contact Info

Product

Resources

About

A Formalism for Learning from Demonstration^*

A Formalism for Learning from Demonstration^*