Tag Archives: Simulation

Using a physical simulator for sampled rollouts in stochastic optimal control

Carius J, Ranftl R, Farshidian F, Hutter M. Constrained stochastic optimal control with learned importance sampling: A path integral approach, The International Journal of Robotics Research. 2022;41(2):189-209, DOI: 10.1177/02783649211047890.

Modern robotic systems are expected to operate robustly in partially unknown environments. This article proposes an algorithm capable of controlling a wide range of high-dimensional robotic systems in such challenging scenarios. Our method is based on the path integral formulation of stochastic optimal control, which we extend with constraint-handling capabilities. Under our control law, the optimal input is inferred from a set of stochastic rollouts of the system dynamics. These rollouts are simulated by a physics engine, placing minimal restrictions on the types of systems and environments that can be modeled. Although sampling-based algorithms are typically not suitable for online control, we demonstrate in this work how importance sampling and constraints can be used to effectively curb the sampling complexity and enable real-time control applications. Furthermore, the path integral framework provides a natural way of incorporating existing control architectures as ancillary controllers for shaping the sampling distribution. Our results reveal that even in cases where the ancillary controller would fail, our stochastic control algorithm provides an additional safety and robustness layer. Moreover, in the absence of an existing ancillary controller, our method can be used to train a parametrized importance sampling policy using data from the stochastic rollouts. The algorithm may thereby bootstrap itself by learning an importance sampling policy offline and then refining it to unseen environments during online control. We validate our results on three robotic systems, including hardware experiments on a quadrupedal robot.

Learning robot simulators

Grant W. Woodford, Mathys C. du Plessis, Bootstrapped Neuro-Simulation for complex robots, . Robotics and Autonomous Systems, Volume 136, 2021 DOI: 10.1016/j.robot.2020.103708.

Robotic simulators are often used to speed up the Evolutionary Robotics (ER) process. Most simulation approaches are based on physics modelling. However, physics-based simulators can become complex to develop and require prior knowledge of the robotic system. Robotics simulators can be constructed using Machine Learning techniques, such as Artificial Neural Networks (ANNs). ANN-based simulator development usually requires a lengthy behavioural data collection period before the simulator can be trained and used to evaluate controllers during the ER process. The Bootstrapped Neuro-Simulation (BNS) approach can be used to simultaneously collect behavioural data, train an ANN-based simulator and evolve controllers for a particular robotic problem. This paper investigates proposed improvements to the BNS approach and demonstrates the viability of the approach by optimising gait controllers for a Hexapod and Snake robot platform.

Improving the realism of a simulator through deep learning

Allevato, A.D., Schaertl Short, E., Pryor, M. et al. , Iterative residual tuning for system identification and sim-to-real robot learning, . Auton Robot 44, 1167–1182 (2020) DOI: 10.1007/s10514-020-09925-w.

Robots are increasingly learning complex skills in simulation, increasing the need for realistic simulation environments. Existing techniques for approximating real-world physics with a simulation require extensive observation data and/or thousands of simulation samples. This paper presents iterative residual tuning (IRT), a deep learning system identification technique that modifies a simulator’s parameters to better match reality using minimal real-world observations. IRT learns to estimate the parameter difference between two parameterized models, allowing repeated iterations to converge on the true parameters similarly to gradient descent. In this paper, we develop and analyze IRT in depth, including its similarities and differences with gradient descent. Our IRT implementation, TuneNet, is pre-trained via supervised learning over an auto-generated simulated dataset. We show that TuneNet can perform rapid, efficient system identification even when the true parameter values lie well outside those in the network’s training data, and can also learn real-world parameter values from visual data. We apply TuneNet to a sim-to-real task transfer experiment, allowing a robot to perform a dynamic manipulation task with a new object after a single observation.

An interesting simulation educational software for control systems engineering based on controlling a quadrotor

S. Khan, M. H. Jaffery, A. Hanif and M. R. Asif, Teaching Tool for a Control Systems Laboratory Using a Quadrotor as a Plant in MATLAB, IEEE Transactions on Education, vol. 60, no. 4, pp. 249-256, DOI: 10.1109/TE.2017.2653762.

This paper presents a MATLAB-based application to teach the guidance, navigation, and control concepts of a quadrotor to undergraduate students, using a graphical user interface (GUI) and 3-D animations. The Simulink quadrotor model is controlled by a proportional integral derivative controller and a linear quadratic regulator controller. The GUI layout’s many components can be easily programmed to perform various experiments by considering the simulation of the quadrotor as a plant; it incorporates control systems (CS) fundamentals such as time domain response, transfer function and state-space form, pole-zero location, root locus, frequency domain response, steady-state error, position and disturbance response, controller design and tuning, unity, and the use of a Kalman filter as a feedback sensor. 3-D animations are used to display the quadrotor flying in any given condition selected by the user. For each simulation, users can view the output response in the form of 3-D animations, and can run time plots. The quadrotor educational tool (QET) helps students in the CS laboratory understand basic CS concepts. The QET was evaluated based on student feedback, grades, satisfaction, and interest in CS.

On how the simplification on physics made in computer games for real-time execution can explain the simplification on physics made by infants when understanding the world

Tomer D. Ullman, Elizabeth Spelke, Peter Battaglia, Joshua B. Tenenbaum, Mind Games: Game Engines as an Architecture for Intuitive Physics, Trends in Cognitive Sciences, Volume 21, Issue 9, 2017, Pages 649-665, DOI: 10.1016/j.tics.2017.05.012.

We explore the hypothesis that many intuitive physical inferences are based on a mental physics engine that is analogous in many ways to the machine physics engines used in building interactive video games. We describe the key features of game physics engines and their parallels in human mental representation, focusing especially on the intuitive physics of young infants where the hypothesis helps to unify many classic and otherwise puzzling phenomena, and may provide the basis for a computational account of how the physical knowledge of infants develops. This hypothesis also explains several ‘physics illusions’, and helps to inform the development of artificial intelligence (AI) systems with more human-like common sense.

Sample-based approximation to POMDPs integrated with forward simulation for robot active exploration, with a nice related work about active exploration in robotics

Mikko Lauri, Risto Ritala, Planning for robotic exploration based on forward simulation, Robotics and Autonomous Systems, Volume 83, 2016, Pages 15-31, ISSN 0921-8890, DOI: 10.1016/j.robot.2016.06.008.

We address the problem of controlling a mobile robot to explore a partially known environment. The robot’s objective is the maximization of the amount of information collected about the environment. We formulate the problem as a partially observable Markov decision process (POMDP) with an information-theoretic objective function, and solve it applying forward simulation algorithms with an open-loop approximation. We present a new sample-based approximation for mutual information useful in mobile robotics. The approximation can be seamlessly integrated with forward simulation planning algorithms. We investigate the usefulness of POMDP based planning for exploration, and to alleviate some of its weaknesses propose a combination with frontier based exploration. Experimental results in simulated and real environments show that, depending on the environment, applying POMDP based planning for exploration can improve performance over frontier exploration.

Limitations of the simulation of physical systems when used in AI reasoning processes for prediction

Ernest Davis, Gary Marcus, The scope and limits of simulation in automated reasoning, Artificial Intelligence, Volume 233, April 2016, Pages 60-72, ISSN 0004-3702, DOI: 10.1016/j.artint.2015.12.003.

In scientific computing and in realistic graphic animation, simulation – that is, step-by-step calculation of the complete trajectory of a physical system – is one of the most common and important modes of calculation. In this article, we address the scope and limits of the use of simulation, with respect to AI tasks that involve high-level physical reasoning. We argue that, in many cases, simulation can play at most a limited role. Simulation is most effective when the task is prediction, when complete information is available, when a reasonably high quality theory is available, and when the range of scales involved, both temporal and spatial, is not extreme. When these conditions do not hold, simulation is less effective or entirely inappropriate. We discuss twelve features of physical reasoning problems that pose challenges for simulation-based reasoning. We briefly survey alternative techniques for physical reasoning that do not rely on simulation.