Learning by an autonomous agent in the pushing domain

Zrimec, Tatjana; Mowforth, P.

doi:10.1016/0921-8890(91)90012-a

Cited by 2 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The "motivation" module guarantees that the system is driven towards acquiring more knowledge about the robot/environment interaction. Reproduced from Zrimec andMowforth (1991). et al (2013) developed a method for predicting contact locations for pushing based on the global and local object shape.…”

Section: Qualitative Modelsmentioning

confidence: 99%

“…Considering other qualitative approaches than those related to affordances, Zrimec and Mowforth ( 1991 ) developed an algorithm for knowledge extraction and representation to predict the effects of pushing. In their experiment, a robot performs random pushes and uses unsupervised learning on those observations.…”

Section: Learning To Predict From Examplesmentioning

confidence: 99%

“… The sequence of operations adopted by Zrimec and Mowforth ( 1991 ) to construct their causality learning model. The robot learns by interacting with the environment in an unsupervised fashion.…”

Section: Learning To Predict From Examplesmentioning

confidence: 99%

“…The “motivation” module guarantees that the system is driven toward acquiring more knowledge about the robot/environment interaction. Reproduced from Zrimec and Mowforth ( 1991 ).…”

Section: Learning To Predict From Examplesmentioning

confidence: 99%

See 3 more Smart Citations

Let's Push Things Forward: A Survey on Robot Pushing

2020

View full text Add to dashboard Cite

As robot make their way out of factories into human environments, outer space, and beyond, they require the skill to manipulate their environment in multifarious, unforeseeable circumstances. With this regard, pushing is an essential motion primitive that dramatically extends a robot's manipulation repertoire. In this work, we review the robotic pushing literature. While focusing on work concerned with predicting the motion of pushed objects, we also cover relevant applications of pushing for planning and control. Beginning with analytical approaches, under which we also subsume physics engines, we then proceed to discuss work on learning models from data. In doing so, we dedicate a separate section to deep learning approaches which have seen a recent upsurge in the literature. Concluding remarks and further research perspectives are given at the end of the paper. Stüber et al. Let's Push Things Forward PROBLEM STATEMENTEven in ideal conditions, such as structured environments where an agent has a complete model of the environment and perfect sensing abilities, the problems of robotic grasping and manipulation are not trivial. By complete model of the environment we mean that physical and geometric properties of the world, such as pose, shape, friction parameters and the mass of the object we wish to manipulate, are exactly known. In fact, the object to be manipulated is indirectly controlled by contacts with a robot manipulator (e.g. pushing by a contacting finger part), and an inverse model (IM), which computes an action to produce the desired motion or set of forces on the object, may not be known. Sometimes forward models (FM) may be fully or partially known, even where IMs are not available. In such cases, an FM can be used to estimate the next state of a system, given the current state and a set of executable actions. This enables planning to be 4. Physics engines. It employs a physics engine as a "black box" to make predictions about the interactions.5. Data-driven. It learns how to predict physical interaction from examples. 6. Deep learning. As the data-driven approaches, it learns how to construct an FM from examples. The key insight is that the deep learning approaches are based on feature extraction.The features highlighted for each approach are as follows.• The assumptions made by the authors on their approach. We highlight i) the quasi-static assumption in the model, ii) if it is a seminal work on 2D shapes, and iii) if the method required a known model of the object to be manipulated.• The type of motion analysed in the paper, such as 1D, planar (2D translation and 1D rotation around the x−axis), or full 3D (3D translation and 3D rotation).• The aim of the paper. We distinguish between predicting the motion of the object, estimating physical parameters, planning pushes, and analysing a push to reach a stable grasp.

show abstract

Section: Qualitative Modelsmentioning

confidence: 99%

Section: Learning To Predict From Examplesmentioning

confidence: 99%

Section: Learning To Predict From Examplesmentioning

confidence: 99%

“…The “motivation” module guarantees that the system is driven toward acquiring more knowledge about the robot/environment interaction. Reproduced from Zrimec and Mowforth ( 1991 ).…”

Section: Learning To Predict From Examplesmentioning

confidence: 99%

See 2 more Smart Citations

Let's Push Things Forward: A Survey on Robot Pushing

2020

View full text Add to dashboard Cite

show abstract

“…Robotics offers a large supply of challenging problems suitable for investigation using learning techniques. The vast majority of recently-developed techniques can be subsumed within the categories of fuzzy logic, [1][2][3][4] connectionist approaches, 5,6 symbolic methods [7][8][9] and genetic algorithms. 10,11 In addition, hybrid versions have been developed which combine two or more of these techniques with the aim of improving or optimising certain control criteria as a result of complementary effects.…”

Section: Introductionmentioning

confidence: 99%

Becoming incrementally reactive: on-line learning of an evolving decision tree array for robot navigation

1999

View full text Add to dashboard Cite

This paper proposes a novel hierarchical multi-layer decision tree for representing reactive robot navigation knowledge. In this representation, the perception space is decomposed into a hierarchical set of worlds reflecting environments which are homogeneous in nature and which vary in complexity in an ordered manner. Each world is used to produce a corresponding decision tree which is trained incrementally. The instantaneous perception of the robot is used to select an appropriate rule from the decision tree and a sequence of rule activations form the complete trajectory. The ability to keep the knowledge complexity manageable and under control is an important aspect of the technique.

show abstract

Learning by an autonomous agent in the pushing domain

Cited by 2 publications

References 3 publications

Let's Push Things Forward: A Survey on Robot Pushing

Let's Push Things Forward: A Survey on Robot Pushing

Becoming incrementally reactive: on-line learning of an evolving decision tree array for robot navigation

Contact Info

Product

Resources

About