China
Africa
Explore chapters and articles related to this topic
A More Sophisticated Example
Published in Sam Freed, AI and Human Thought and Emotion, 2019
Discussing the experiment recorded in the video “learn1.avi” (see link on the top of Section 12.4): In this simulation, there was a bug in the physics engine (leading to an undefined state), so occasionally the car-racing game is reset to its initial state, without resetting the AI software. The question of how skills are learnt best, in an ongoing engagement with the problem or with repetitive restarts, remains open.
Embodied AI, or the tale of taming the fungus eater
Published in Arkapravo Bhaumik, From AI to Robotics, 2018
Various routes have been taken by researchers to evaluate the performance of an autonomous AI agent, however there is a lack of consensus on a particular approach. Since AI agents are situated, they are significantly different from conventional control systems manipulated using feedback. In conventional systems the performance is usually the quotient of the average deviation of control variables from their predicted values, the sensitivity of the controller to noise, the stability of the controller dynamics and repeatability within the realms of acceptable error. However, in situated agents, the desired robot behaviour is obtained as an emergent property of the agent-environment interactions. Therefore there need to be methods which differ significantly from the conventional types. Extrapolating conventional ideas; make the robot repeat a given task a large number of times and the percentage of success will quantify performance. As an illustration, an automated robotic waiter can be evaluated on the number of times it can serve correctly without fumbling. An appreciable high percentage will confirm the consistency of performance. The obvious shortcoming is that this robotic waiter, when performing some task other than serving, will need another set of benchmarking to suit that task. Also, as a demerit, this sort of an approach will fail to cover all types of tasks, viz. unknown terrain, dynamic tasks, effective human-robot and robot-robot interactions and faulty hardware. However, these methods due to their simplicity, remain favourites among researchers and most research papers resort to such evaluations.Correlate actual performance to simulation [163, 371]; though this paradigm is an oxymoron as it is meant to relate a situated phenomenon to a non-situated simulated process, even then this approach remains another favourite in the research community. Present-day software simulation methods are very sophisticated, can mimic a real environment, usually have a physics engine and yield nearly real-time performance. However, simulation still has its pitfalls as it fails to provide for realistic physics for friction, magnetic interactions, wear and tear, fracture, effects of moisture, second-order effects etc. Further, this will bring into play the benchmarking, performance, computational capacity and the hardware aspects of the machine on which the simulation is run, viz. RAM, data rate, CPU power, clock etc. Also, as in the previous method, this approach also fails to account for unknown terrain and dynamic tasks.
State-based verification of industrial control programs with the use of a digital model
Published in International Journal of Computer Integrated Manufacturing, 2023
Matthias Schamp, El-Houssaine Aghezzaf, Johannes Cottyn
This chapter presents two cases of the use of the proposed workflow on a basic model to demonstrate the functionality. The first case is a complete system to demonstrate the interaction of individual subsystems. The second case is a subsystem of the previous case and is used to quantify the benefits of the automatic verification. The workflow is software independent; Visual Components is used in the use cases. Visual Components is an emulation tool with an API that allows to add functionality to the software and interact with the model. It provides a communication structure between the industrial controller and the Digital Model. The physics engine in the software enables the inclusion of physical behaviour (collisions, gravity) in the simulation.
LP-based velocity profile generation for robotic manipulators
Published in International Journal of Control, 2018
We simulate the movements of a 3-DOF robotic manipulator in V-REP robot simulator software (Coppelia Robotics, 2016). The program uses a physics engine to simulate real-world physics and object interactions. With this simulation environment, the calculation time of the different methods can be compared. The impact of the approximations used for the first and second derivatives of the path can be also examined.