Data-Efficient Learning for Complex and Real-Time Physical Problem Solving Using Augmented Simulation

Ota, Kei; Jha, Devesh K.; Romeres, Diego; Baar, Jeroen van; Smith, Kevin A.; Semitsu, Takayuki; Oiki, Tomoaki; Sullivan, Alan; Nikovski, Daniel; Tenenbaum, Joshua B.

doi:10.1109/lra.2021.3068887

Cited by 13 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, [90] demonstrates the combination of ACT-R and a physics engine to enhance the predictive power of the cognitive model to better replicate human behavior. Additionally, [5,86,87] demonstrate integrating a physics model into training of a learned behavior model. In [86,87], this allows training of the behavior in a simulated environment followed by a transition to the real world.…”

Section: Applications and Recent Resultsmentioning

confidence: 99%

“…Additionally, [5,86,87] demonstrate integrating a physics model into training of a learned behavior model. In [86,87], this allows training of the behavior in a simulated environment followed by a transition to the real world. The agent can learn a approximate solution based on the simulator and then learn a translation which maps the simulation to the real world.…”

Section: Applications and Recent Resultsmentioning

confidence: 99%

“…Engines such as Unity or MuJoCo [116] demonstrate motion of objects in physical environments and can provide realism to object motion for observations made by artificial agents. These models of system behavior can provide an agent with an internal estimator for world dynamics to support prediction and planning [5,86,87]. This lets a learner generate predicted future states for reasoning and planning.…”

Section: Relevant Survey(s)mentioning

confidence: 99%

See 2 more Smart Citations

Modeling Human Behavior Part I -- Learning and Belief Approaches

Fuchs¹,

Passarella²,

Conti³

2022

Preprint

View full text Add to dashboard Cite

There is a clear desire to model and comprehend human behavior. Trends in research covering this topic show a clear assumption that many view human reasoning as the presupposed standard in artificial reasoning. As such, topics such as game theory, theory of mind, machine learning, etc. all integrate concepts which are assumed components of human reasoning. These serve as techniques to attempt to both replicate and understand the behaviors of humans. In addition, next generation autonomous and adaptive systems will largely include AI agents and humans working together as teams. To make this possible, autonomous agents will require the ability to embed practical models of human behavior, which allow them not only to replicate human models as a technique to "learn", but to to understand the actions of users and anticipate their behavior, so as to truly operate in symbiosis with them. The main objective of this paper it to provide a succinct yet systematic review of the most important approaches in two areas dealing with quantitative models of human behaviors. Specifically, we focus on (i) techniques which learn a model or policy of behavior through exploration and feedback, such as Reinforcement Learning, and (ii) directly model mechanisms of human reasoning, such as beliefs and bias, without going necessarily learning via trial-and-error.CCS Concepts: • Human-centered computing; • General and reference → Surveys and overviews;

show abstract

Section: Applications and Recent Resultsmentioning

confidence: 99%

Section: Applications and Recent Resultsmentioning

confidence: 99%

Section: Relevant Survey(s)mentioning

confidence: 99%

See 1 more Smart Citation

Modeling Human Behavior Part I -- Learning and Belief Approaches

Fuchs¹,

Passarella²,

Conti³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Another interesting line of work would to be to include a Reinforcement learning algorithm to get model updates [26] during learning.…”

Section: Discussionmentioning

confidence: 99%

Chance-Constrained Optimization in Contact-Rich Systems for Robust Manipulation

Shirai¹,

Jha²,

Raghunathan³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents a chance-constrained formulation for robust trajectory optimization during manipulation. In particular, we present a chance-constrained optimization for Stochastic Discrete-time Linear Complementarity Systems (SDLCS). To solve the optimization problem, we formulate Mixed-Integer Quadratic Programming with Chance Constraints (MIQPCC). In our formulation, we explicitly consider joint chance constraints for complementarity as well as states to capture the stochastic evolution of dynamics. We evaluate robustness of our optimized trajectories in simulation on several systems. The proposed approach outperforms some recent approaches for robust trajectory optimization for SDLCS.

show abstract

“…It is noted that a lot of research in the machine learning community has been fueled by the availability of opensource software that allows quick prototyping of machine learning models (Abadi et al 2016). Our work in this paper is motivated by the understanding that, in the near future, robots could be equipped with tools that allow specification of dynamics (e.g., the physics engines) as well as highperformance optimization routines that allow solution to mathematical programs for model-based optimization and control (Ota et al 2021). With this motivation, we present a python-based robotic control and optimization package (called PYROBOCOP) that allows solution to a large class of mathematical programs with nonlinear constraints.…”

Section: Introductionmentioning

confidence: 99%

PYROBOCOP : Python-based Robotic Control & Optimization Package for Manipulation and Collision Avoidance

Raghunathan¹,

Jha²,

Romeres³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

PYROBOCOP is a lightweight Python-based package for control and optimization of robotic systems described by nonlinear Differential Algebraic Equations (DAEs). In particular, the package can handle systems with contacts that are described by complementarity constraints and provides a general framework for specifying obstacle avoidance constraints. The package performs direct transcription of the DAEs into a set of nonlinear equations by performing orthogonal collocation on finite elements. The resulting optimization problem belongs to the class of Mathematical Programs with Complementarity Constraints (MPCCs). MPCCs fail to satisfy commonly assumed constraint qualifications and require special handling of the complementarity constraints in order for NonLinear Program (NLP) solvers to solve them effectively. PYROBOCOP provides automatic reformulation of the complementarity constraints that enables NLP solvers to perform optimization of robotic systems. The package is interfaced with ADOL-C (Griewank et al. 1996) for obtaining sparse derivatives by automatic differentiation and IPOPT (W ächter and Biegler 2006) for performing optimization. We demonstrate the effectiveness of our approach in terms of speed and flexibility. We provide several numerical examples for several robotic systems with collision avoidance as well as contact constraints represented using complementarity constraints. We provide comparisons with other open source optimization packages like CasADi and Pyomo.

show abstract

Data-Efficient Learning for Complex and Real-Time Physical Problem Solving Using Augmented Simulation

Cited by 13 publications

References 27 publications

Modeling Human Behavior Part I -- Learning and Belief Approaches

Modeling Human Behavior Part I -- Learning and Belief Approaches

Chance-Constrained Optimization in Contact-Rich Systems for Robust Manipulation

PYROBOCOP : Python-based Robotic Control & Optimization Package for Manipulation and Collision Avoidance

Contact Info

Product

Resources

About