In the past two decades, unmanned aerial vehicles (UAVs) have demonstrated their efficacy in supporting both military and civilian applications, where tasks can be dull, dirty, dangerous, or simply too costly with conventional methods. Many of the applications contain tasks that can be executed in parallel, hence the natural progression is to deploy multiple UAVs working together as a force multiplier. However, to do so requires autonomous coordination among the UAVs, similar to swarming behaviors seen in animals and insects. This paper looks at flocking with small fixed-wing UAVs in the context of a model-free reinforcement learning problem. In particular, Peng's Q(λ)$with a variable learning rate is employed by the followers to learn a control policy that facilitates flocking in a leader-follower topology. The problem is structured as a Markov decision process, where the agents are modeled as small fixed-wing UAVs that experience stochasticity due to disturbances such as winds and control noises, as well as weight and balance issues. Learned policies are compared to ones solved using stochastic optimal control (i.e., dynamic programming) by evaluating the average cost incurred during flight according to a cost function. Simulation results demonstrate the feasibility of the proposed learning approach at enabling agents to learn how to flock in a leader-follower topology, while operating in a nonstationary stochastic environment.

With recent advances in mobile robotics, autonomous systems, and artificial intelligence, there is a growing expectation that robots are able to solve complex problems. Many of these problems require multiple robots working cooperatively in a multi-robot system. Complex tasks may also include the interconnection of task-level specifications with robot motion-level constraints. Many recent works in the literature use multiple mobile robots to solve these complex tasks by integrating task and motion planning. We survey recent contributions to the field of combined task and motion planning for multiple mobile robots by categorizing works based on their underlying problem representations, and we identify possible directions for future research. We propose a taxonomy for task and motion planning based on system capabilities, applicable to multi-robot and single-robot systems.

Crack detection and measurement in civil structures has been a constant field of research. Conventionally, a technician is responsible to detect and measure cracks in the field. In this paper, a system based on machine vision concepts has been developed with the goal to automate the crack measurement process. Using this method with only a single camera installed in a truck or even in a robot, a sequence of images is processed and the crack dimensions are estimated. The experimental results validate the application of the proposed method for real structures.

In order for teams of unmanned aerial vehicles (UAVs) to collaborate and cooperate to perform challenging group tasks, intelligent and flexible control strategies are required. One of the complex behaviors required of a team of UAVs is dynamic encirclement, which is a tactic that can be employed for persistent surveillance and/or to neutralize a target by restricting its movement. This tactic requires a high level of cooperation such that the UAVs maintain a desired and proper encirclement radius and angular velocity around the target. In this paper, model predictive control (MPC) is used to model and implement controllers for the problem of dynamic encirclement. The linear and nonlinear control policies proposed in this paper are applied as a high-level controller to control multiple UAVs to encircle a desired target in simulations and real-time experiments with quadrotors. The nonlinear solution provides a theoretical analysis of the problem, while the linear control policy is used for real-time operation via a combination of MPC and feedback linearization applied to the nonlinear UAV system. The contributions of this paper lie in the implementation of MPC to solve the problem of dynamic encirclement of a team of UAVs in real time and the application of theoretical stability analysis to the problem.

Stereo vision is widely used in many 3-D image applications. In this paper, we present a methodology to estimate the localization of objects in 3-D scenes using collaborative robots. Using this method, the robots are able to measure the location of objects using only a single camera installed on each one of them. From one pair of images, each one acquired by a different robot, the method locates homologous points, and then rebuilds the object by using equations for coordinate transformations. The experimental results validate the application of the proposed method for the measurement of the pose of objects in autonomous robotic applications.

With advances in computing power, stereo vision has become an essential part of navigation applications. However, there may be instances wherein insufficient image data precludes the estimation of navigation parameters. Earlier, a novel vision-based velocity estimation method was developed by the authors, which suffered from the aforementioned drawback. In this paper, the vision-based navigation method has been integrated with a unique low-cost reduced inertial sensor system to bridge the navigation gap using one gyroscope and two accelerometers along with the inputs from wheel speed sensors. The integrated system is based on the extended Kalman filter and was tested on three trajectories with the introduction of vision data gaps. The system showed promising results for autonomous land vehicle applications.