Despite the fact that Second Order Similarity (SOS) has been used with significant success in tasks such as graph matching and clustering, it has not been exploited for learning local descriptors. In this work, we explore the potential of \sos in the field of descriptor learning by building upon the intuition that a positive pair of matching points should exhibit similar distances with respect to other points in the embedding space. Thus, we propose a novel regularization term, named Second Order Similarity Regularization (SOSR), that follows this principle. By incorporating SOSR into training, our learned descriptor achieves state-of-the-art performance on several challenging benchmarks containing distinct tasks ranging from local patch retrieval to structure from motion. Furthermore, by designing a von Mises-Fischer distribution based evaluation method, we link the utilization of the descriptor space to the matching performance, thus demonstrating the effectiveness of our proposed SOSR. Extensive experimental results, empirical evidence, and in-depth analysis are provided, indicating that SOSR can significantly boost the matching performance of the learned descriptor.

Evolutionary algorithms have previously shown promise in generating controllers for legged robots. Multiple evaluations across many evolutionary generations are typically required - simulators are frequently used to accommodate this. However, performance degradation is frequently observed when transferring controllers from simulation to reality due to inconsistencies between the two. In this paper we demonstrate a testbed that permits repeated, direct evolution of hexapod controllers as a closed-loop system. The testbed uses a two-stage evolutionary process. In stage 1, a multi-objective evolutionary algorithm spreads a population of controllers across a space of desirable criteria. The second stage allows for specific criteria to be selected for on a per-mission basis, with promising initial controller parameters taken from the first stage. As the optimisation occurs directly on the robot, performance is guaranteed. Furthermore, controllers can be made specific to irregularities in e.g., motor wear, and robot mass distribution, creating controllers that are sensitive to the hardware state of the individual robot.