RECORD
Information-theoretic Model Identification and Policy Search using Physics Engines with Application to Robotic Manipulation
Robotics · Submitted 22 Mar 2017
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experimental results both in simulation and using a real robot indicate that the proposed method outperforms state-of-the-art model-free reinforcement learning approaches.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
We consider the problem of a robot learning the mechanical properties of objects through physical interaction with the object, and introduce a practical, data-efficient approach for identifying the motion models of these objects. The proposed method utilizes a physics engine, where the robot seeks to identify the inertial and friction parameters of the object by simulating its motion under different values of the parameters and identifying those that result in a simulation which matches the observed real motions. The problem is solved in a Bayesian optimization framework. The same framework is used for both identifying the model of an object online and searching for a policy that would minimize a given cost function according to the identified model. Experimental results both in simulation and using a real robot indicate that the proposed method outperforms state-of-the-art model-free reinforcement learning approaches.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | We consider the problem of a robot learning the mechanical properties of objects through physical interaction with the object, and introduce a practical, data-efficient approach for identifying the motion models of these objects. | contribution 0.79 | 0.72 | 0.06 | asserted 0.95 |
| s1 | The proposed method utilizes a physics engine, where the robot seeks to identify the inertial and friction parameters of the object by simulating its motion under different values of the parameters and identifying those that result in a simulation which matches the observed real motions. | method 1.00 | 0.75 | 0.04 | asserted 1.00 |
| s2 | The problem is solved in a Bayesian optimization framework. | method 1.00 | 0.71 | 0.03 | asserted 1.00 |
| s3 | The same framework is used for both identifying the model of an object online and searching for a policy that would minimize a given cost function according to the identified model. | method 0.69 | 0.84 | 0.08 | asserted 1.00 |
| s4 | Experimental results both in simulation and using a real robot indicate that the proposed method outperforms state-of-the-art model-free reinforcement learning approaches. | result 1.00 | 0.95 | 0.82 | asserted 0.57 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
We consider the problem of a robot learning the mechanical properties of objects through physical interaction with the object, and introduce a practical, data-efficient approach for identifying the motion models of these objects. The proposed method utilizes a physics engine, where the robot seeks to identify the inertial and friction parameters of the object by simulating its motion under different values of the parameters and identifying those that result in a simulation which matches the observed real motions. The problem is solved in a Bayesian optimization framework. The same framework is used for both identifying the model of an object online and searching for a policy that would minimize a given cost function according to the identified model. Experimental results both in simulation and using a real robot indicate that the proposed method outperforms state-of-the-art model-free reinforcement learning approaches.
Human review
How the literature uses it
2 arXiv papers cite this in 2 sentences
Papers citing it · 1 sentence without a confident label
Cites it as background 1 paper
-
Zhu et al. use a simulator as a predictive model [ref] .
COCOI: Contact-aware Online Context Inference for Generalizable Non-planar Pushing · Related Work · 0.96
What it cites
Uses data or values from 1 paper
-
The proposed method was also tested using a large scale pushing dataset [ref] .
More than a Million Ways to Be Pushed: A High-Fidelity Experimental Dataset of Planar Pushing · Results · 1.00
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.