AbstractThere is currently a strongly growing interest in obtaining optimal control solutions for vehicle manoeuvres, both order to understand behaviour and, perhaps more importantly, devise improved safety systems, either by direct deployment of the or including mimicked driving techniques professional drivers. However, it non-trivial find right combination models, optimisation criteria, and tools get useful results above purposes. Here, platform investigation these aspects developed based...

Enabling resilient autonomous motion planning requires robust predictions of surrounding road users' future behavior. In response to this need and the associated challenges, we introduce our model titled MTP-GO. The encodes scene using temporal graph neural networks produce inputs an underlying model. is implemented ordinary differential equations where state-transition functions are learned with rest Multimodal probabilistic obtained by combining concept mixture density Kalman filtering....

The problem of planning a trajectory for robots starting in an initial state and reaching final desired interval time is tackled. We consider Model Predictive Control as approach to the point-to-point generation. use developed strategy generate trajectories transferring robot, fulfilling computational real-time requirements. Experiments on industrial robot ball-catching scenario show effectiveness approach.

Autonomous vehicle functions in safety-critical situations show promise reducing the risk and saving lives accidents compared to existing safety systems. Consequently, it is from many perspectives advantageous be able quantify potential benefits of new autonomous systems for maneuvers at-the-limit tire friction. Here, estimate terms saved reduced degree injuries new, not yet systems, a framework has been developed by combining available historic data, form crash databases, statistical...

An approach to resilient planning and control of autonomous vehicles in multi-vehicle traffic scenarios is proposed. The proposed method based on model predictive (MPC), where alternative predictions the surrounding are determined automatically such that they intentionally adversarial ego vehicle. This provides robustness against inherent uncertainty predictions. To reduce conservatism, an assumption other agents no ill intent formalized. Simulation results from highway driving show...

This article proposes an interaction and safety-aware motion-planning method for autonomous vehicle in uncertain multi-vehicle traffic environments. The integrates the ability of interaction-aware interacting multiple model Kalman filter (IAIMM-KF) to predict interactive multi-modal maneuvers surrounding vehicles, advantage predictive control (MPC) planning optimal trajectory dynamic prediction uncertainties, containing both maneuver uncertainties are considered computing reference targets...

We consider the problem of tool position and orientation state estimation for robot manipulators in workspace by sensor fusion internal joint measurements with inertial measurement unit data. A prerequisite this to be successful is accurate calibration sensors used. Therefore, we discuss a method respect end-effector, which straightforward apply on an arbitrary industrial manipulator. also two different state-estimation algorithms requiring minimum modeling; first based extended Kalman...

The ability to predict the future trajectories of traffic participants is crucial for safe and efficient operation autonomous vehicles. In this paper, a diffusion-based generative model multi-agent trajectory prediction proposed. capable capturing complex interactions between environment, accurately learning multimodal nature data. effectiveness approach assessed on large-scale datasets real-world scenarios, showing that our outperforms several well-established methods in terms accuracy. By...

The strong process forces arising during highspeed machining operations, combined with the limited stiffness of industrial robots, have hampered usage robots in high-end milling tasks. However, since such manipulators may offer flexible and cost-effective solutions, a three-dimensional piezo-actuated compensation mechanism, which aims to compensate for positioning errors robot, has earlier been developed. A prototype model-based control scheme position utilizing LQG control, proposed. main...

The problem of planning a trajectory for robots starting in an initial state and reaching final desired interval time is tackled. We propose approach based on model predictive control to solve the point-to-point generation given time. discuss various choices models, objective functions, constraints generating trajectories transfer robot, while respecting physical limitations motion as well fulfilling computational real-time requirements. Extensive simulation results illustrate use approach,...

Given their flexibility and encouraging performance, deep-learning models are becoming standard for motion prediction in autonomous driving. However, with great comes a lack of interpretability possible violations physical constraints. Accompanying these data-driven methods differentially-constrained to provide physically feasible trajectories is promising future direction. The foundation this work previously introduced graph-neural-network-based model, MTP-GO. neural network learns compute...

Stability control of a vehicle in autonomous safety-critical at-the-limit manoeuvres is analysed from the perspective lane keeping or changing, rather than that yaw as traditional ESC systems. An optimal formulation developed, where optimisation criterion linear combination initial and final velocity manoeuvre. Varying interpolation parameter this turns out to result an interesting family braking steering patterns stabilising manoeuvres. The two different strategies lane-keeping are shown be...

There is currently a strongly growing interest in obtaining optimal control solutions for vehicle maneuvers, both order to understand behavior and devise improved safety systems, either by direct deployment of the or including mimicked driving techniques professional drivers. However, it nontrivial find right mix models, formulations, optimization tools get useful results above purposes. Here, platform developed based on state-of-the-art tool together with adoption existing where especially...

This paper presents a method for modeling and control of piezo-actuated high-dynamic compensation mechanism usage together with an industrial robot during machining operation, such as milling in aluminium. The spindle was attached to the held workpiece. Due inherent resonant character mechanical constructions this type, nonlinear phenomena appearing piezo actuators, is challenging problem. models construction, experimentally identified using subspace-based identification methods. A...

This paper presents a method for modeling and control of piezo-actuated high-dynamic compensation mechanism usage together with an industrial robot during machining operation, such as milling in aluminium.The spindle was attached to the held workpiece.Due inherent resonant character mechanical constructions this type, nonlinear phenomena appearing piezo actuators, is challenging problem.This models construction, experimentally identified using subspace-based identification methods.A...

Handling of critical situations is an important part in the architecture autonomous vehicle. A controller for collision avoidance developed based on a wary strategy that assumes least tire-road friction which maneuver still feasible. Should be greater, makes use this, and performs better. The uses acceleration-vector reference obtained from optimal control friction-limited particle, whose applicability verified by using numerical optimization full vehicle model. By employing analytical tire...

Formulae display:?Mathematical formulae have been encoded as MathML and are displayed in this HTML version using MathJax order to improve their display. Uncheck the box turn off. This feature requires Javascript. Click on a formula zoom.