Search

Stereo correspondence is a well-established research topic and has spawned categories of algorithms combining several processing steps and strategies. One core part to stereo correspondence is to determine matching cost between the two images, or patches from the two images. Over the years several different cost metrics have been proposed, one being the Census Transform (CT). The CT is well proven for its robust matching, especially along object boundaries, with respect to outliers and radiometric differences. The CT also comes at a low computational cost and is suitable for hardware implementation. Two key developments to the CT are non-centric and sparse comparison schemas, to increase matching performance and/or save computational resources. Recent CT algorithms share both traits but are handcrafted, bounded with respect to symmetry, edge lengths and defined for a specific window size. To overcome this, a Genetic Algorithm (GA) was applied to the CT, proposing the Genetic Algorithm Census Transform (GACT), to automatically derive comparison schemas from example data. In this paper, FPGA-based hardware acceleration of GACT, has enabled evaluation of census windows of different size and shape, by significantly reducing processing time associated with training. The experiments show that lateral GACT windows produce better matching accuracy and require less resources when compared to square windows.

Trajectory tracking for an autonomous bicycle is considered in this paper. The trajectory tracking controller is designed using a Model Predictive Controller with constraints on the lean, steer, and heading angle as well as the position coordinates of the bicycle. The output from the trajectory tracking controller is the desired lean angle and forward velocity. Furthermore, a PID controller is designed to follow the desired lean angle, while maintaining balance, by actuation of the handlebar. The proposed control strategy is evaluated in numerous simulations where a realistic nonlinear model of the bicycle is traversing a go-kart track and a short track with narrow curves. The Hausdorff distance and Mean Squared Error are considered as measurements of the performance. The results show that the bicycle successfully can track desired trajectories at varying velocities.

The use of multiagent systems (MASs) in real-world applications keeps increasing, and diffuses into new domains, thanks to technological advances, increased acceptance, and demanding productivity requirements. Being able to automate the generation of mission plans for MASs is critical for managing complex missions in realistic settings. In addition, finding the right level of abstraction to represent any generic MAS mission is important for being able to provide general solution to the automated planning problem. In this article, we show how a mission for heterogeneous MASs can be cast as an extension of the traveling salesperson problem (TSP), and we propose a mixed-integer linear programming formulation. In order to solve this problem, a genetic mission planner (GMP), with a local plan refinement algorithm, is proposed. In addition, the comparative evaluation of CPLEX and GMP is presented in terms of timing and optimality of the obtained solutions. The algorithms are benchmarked on a proposed set of different problem instances. The results show that, in the presence of timing constraints, GMP outperforms CPLEX in the majority of test instances.

Multi-Agent Systems (MASs) have been widely adopted in robotics, as a means to solve complex missions by subdividing them into smaller tasks. In such a context, Multi-Robot Task Allocation (MRTA) has been a relevant research area, with the main aim of providing formulations and solutions to different mission configurations, in order to optimize the planning and the execution of complex missions utilizing multiple robots.In recent years, robotic systems have become more powerful thanks to the adoption of novel computing platforms, enabling an increased level of parallelism, in terms of sensing, actuation, and computation. As a result, more complex missions can be achieved, at the cost of an increased complexity for the optimization of the mission planning.In this paper, we first introduce the distinction between physical and virtual tasks of the robots, and their relation in terms of parallel execution. Therefore, we propose a mathematical formalization of the mission planning problem for Multi-Task (MT) robots, in the presence of tasks that require only a Single-Robot (SR) to complete, and in the presence of Time-Extended Assignments (TAs). The problem is modeled with a Mixed-Integer Linear Programming (MILP) formulation, with the objective of minimizing the total makespan of the mission, exploiting the potential (physical and virtual) parallelism of the robots. The model is validated over some representative scenarios, and their respective solutions are obtained with the CPLEX optimization tool, showing the generality of the proposed formulation.

Multi-Agent Systems have received a tremendous amount of attention in many areas of research and industry, especially in robotics and computer science. With the increased number of agents in missions, the problem of allocation of tasks to agents arose, and it is one of the most fundamental classes of problems in robotics, formally known as the Multi-Robot Task Allocation (MRTA) problem. MRTA encapsulates numerous problem dimensions, and it aims at providing formulations and solutions to various problem configurations, i.e., complex multi-robot missions. One dimension of the MRTA problem has not caught much of the research attention. In particular, problem configurations including Multi-Task (MT) robots have been neglected. However, the increase in computational power, in robotic systems, has allowed the utilization of parallel task execution. This in turn had the benefit of allowing the creation of more complex robotic missions; however, it came at the cost of increased problem complexity. To overcome the aforementioned problem, we introduce the distinction between physical and virtual tasks and their mutual relationship in terms of parallel task execution. To fill in the gap in the literature related to MT robot problem configurations, we provide a formalization of the mission planning problem, using MT robots, in the form of Integer Linear Programming and Constraint Programming (CP), to minimize the mission makespan. The models are validated in CPLEX and CP Optimizer on the set of benchmarks. Moreover, we provide a comprehensive performance analysis of both solvers, exploring their scalability and solution quality.