Autonomous driving has been the subject of incre- ased interest in recent years both industry and academia. Serious efforts are being pursued to address legal, technical, logistical problems make autonomous cars a viable option for everyday transportation. One significant challenge is time effort required verification validation decision control algorithms employed these vehicles ensure safe comfortable experience. Hundreds thousands miles tests achieve well calibrated system that capable...

In this paper, we propose hierarchical control architecture for a system that does border or perimeter patrol using unmanned air vehicles (AUV). By mean specific way of organizing the motion and navigation functions performed by UAV. It is convenient to organize into layers. This way, complex design problem partitioned number more manageable subproblems are addressed in separate paper discusses vehicle requirements maps them onto layered architecture. The formalization hierarchy accomplished...

included. Simulations are compared with previous modeling efforts, which neglected the wings’ mass and associated inertial coupling effects on body. show a qualitative consistency for nonlinear model wing when different aerodynamic models chosen as inputs. Simulation results significant differenceinthemodelbehaviorwhenthemassofthewings,initiallysetat5.7%ofthebodymass,isincludedversus whenthemassisneglected.Asthemassofthewingsisdecreased,thesimulationresultsofthemodelwithwingeffects...

Motivated by the need for simulation tools testing, verification and validation of autonomous driving systems that operate in traffic consisting both human-driven vehicles, we propose a game-theoretic framework modeling interactive behavior vehicles at uncontrolled intersections. The proposed vehicle interaction model is based on novel formulation dynamic games with multiple concurrent leader-follower pairs, induced from common rules. Based results various intersection scenarios, show...

In this paper, we propose a decision making algorithm for autonomous vehicle control at roundabout intersection. The is based on game-theoretic model representing the interactions between ego and an opponent vehicle, adapts to online estimated driver type of vehicle. Simulation results are reported.

For a foreseeable future, autonomous vehicles (AVs) will operate in traffic together with human-driven vehicles. Their planning and control systems need extensive testing, including early-stage testing simulations where the interactions among autonomous/human-driven are represented. Motivated by for such simulation tools, we propose game-theoretic approach to modeling vehicle interactions, particular, urban environments unsignalized intersections. We develop models heterogeneous (in terms of...

Merging is, in general, a challenging task for both human drivers and autonomous vehicles, especially dense traffic, because the merging vehicle typically needs to interact with other vehicles identify or create gap safely merge into. In this paper, we consider problem of control forced scenarios. We propose novel game-theoretic controller, called Leader-Follower Game Controller (LFGC), which interactions between ego priori uncertain driving intentions is modeled as partially observable...

A large focus of the Unmanned Aerial Vehicle (UAV) community has been shifted to addressing requirements necessary for managing systems UAVs. The ability automate process tracking and responding health UAVs contributes reliable persistent operation multiple UAV systems. In particular, automation their resources removes a critical, frequent, time consuming task from an operator's workload. We have developed battery swapping mechanism capable `refueling' autonomously. This paper presents...

In this paper, we discuss a game theoretic approach to model the time-extended, multi-step, and interactive decision making of vehicles at unsignalized intersections. The vehicle interaction is then used define an autonomous controller. Simulation results for common intersection scenario are reported.

Codiagnosability and coobservability in discrete event systems where observations are dynamic considered. Instead of having a fixed set observable events, the observation an is (trace-dependent) this paper. A procedure developed to transform problem codiagnosability context observations. This proves that problems transformable enables us leverage large literature available for solve coobservability. Furthermore, case observations, known polynomial-complexity tests property based on verifier...

A hierarchical game theoretic decision making framework is exploited to model driver decisions and interactions in traffic. In this paper, we apply develop a simulator evaluate various existing autonomous driving algorithms. Specifically, two algorithms, based on Stackelberg policies trees, are quantitatively compared traffic scenario where all the human-driven vehicles modeled using presented approach.

This paper considers the problem of path planning for a team unmanned aerial vehicles performing surveillance near friendly base. The do not possess sensors with automated target recognition capability and, thus, rely on communicating unattended ground placed roads to detect and image potential intruders. is motivated by persistent intelligence, surveillance, reconnaissance base defense missions. formulated shown be intractable. A heuristic algorithm coordinate during pursuit presented....

This paper describes a game theoretical model of traffic where multiple drivers interact with each other. The is developed using hierarchical reasoning, human behavior, and reinforcement learning. It assumed that the can observe only partial state they are in therefore although environment satisfies Markov property, it appears as non-Markovian to drivers. Hence, driver implicitly has find policy, i.e. mapping from observations actions, for Partially Observable Decision Process. In this...

Decision-making for autonomous driving is challenging, considering the complex interactions among multiple traffic agents (including vehicles (AVs), human-driven vehicles, and pedestrians) computational load needed to evaluate these interactions. This paper develops two general potential game-based frameworks, namely, finite continuous games, decision-making in driving. The frameworks account AVs' types of action spaces, i.e., respectively. developed provide theoretical guarantees existence...

Motivated by the growing need to accommodate large transient thrust and electrical load requests in future more-electric aircraft, a coordinated control strategy for gas turbine engine, generators, energy storage is developed. An advanced two-generator configuration, with each generator connected shaft of treated. Model predictive maximizes system performance protects this against constraint violations. The controller design exploits rate-based linear prediction models. In addition, an...

Spacecraft relative motion planning is concerned with the design and execution of maneuvers to a nominal target. These types are frequently used in missions such as rendezvous docking, satellite inspection, formation flight, where exclusion zones representing spacecraft or other obstacles must be avoided. The presence these leads nonlinear nonconvex constraints that satisfied. In this paper, novel approach obstacle avoidance thrust developed. This based on graph search applied virtual net...

In this paper, we present a safe deep reinforcement learning system for automated driving. The proposed framework leverages merits of both rule-based and learning-based approaches safety assurance. Our consists two modules namely handcrafted dynamically-learned safety. module is heuristic rule based on common driving practice that ensure minimum relative gap to traffic vehicle. On the other hand, data-driven learns patterns from data. Specifically, dynamically-leaned incorporates model...

In this paper, we propose a hierarchical control architecture for an enhanced variant of Cooperative Adaptive Cruise Control (CACC), which would include some Forward Collision Warning (CFCW) functionality. Simply put, CACC system is more sophisticated cruise control. By mean specific way organizing the motion and navigation functions performed by cars. It convenient to organize into layers. This way, complex design problem partitioned number manageable sub-problems that are addressed in...

Motivated by cooperative exploration missions, this paper considers constant velocity, level flight path planning for Unmanned Air Vehicles (UAVs) equipped with range limited, omni-directional sensors. These active energy-based sensors collect information about objects of interest at rates that depend on the to according Shannon's channel capacity equation, where signal-to-noise ratio is governed radar equation. The mission UAVs travel through a given area and specified amount each object...

This paper considers centralized and decentralized control problems for partially-observed discrete event systems where sensor readings are assumed to be costly reasons of bandwidth, energy, or security. The supervisory controllers, agents, dynamically request sensors as needed observe the trajectories system correctly implement given feedback law. Thus, each may turned on/off several times along a trajectory. Different policies dynamic activation can used by agents. A set is said minimal if...