Obstacle Avoidance and Environmental Adaptability Analysis of Snake-like Robot Based on Deep Learning

Aiming at the problems of high complexity and low accuracy of visual depth map feature recognition, a graph recognition algorithm based on principal component direction depth gradient histogram (pca-hodg) is designed in this study. In order to obtain high-quality depth map, it is necessary to calculate the parallax of the visual image. At the same time, in order to obtain the quantized regional shape histogram, it is necessary to carry out edge detection and gradient calculation on the depth map, then reduce the dimension of the depth map combined with the principal component, and use the sliding window detection method to reduce the dimension again to realize the feature extraction of the depth map. The results show that compared with other algorithms, the pca-hodg algorithm designed in this study improves the average classification accuracy and significantly reduces the average running time. This shows that the algorithm can reduce the running time by reducing the dimension, extract the depth map features more accurately, and has good robustness.

From Hand to Eye With the Devil In-Between: Which Cognitive Mechanisms Underpin the Benefit From Handwriting Training When Learning Visual Graphs?

Cognitive science has recently shown a renewed interest on the benefit from training in handwriting (HW) when learning visual graphs, given that this learning experience improves more subsequent visual graph recognition than other forms of training. However, the underlying cognitive mechanism of this HW benefit has been elusive. Building on the 50 years of research on this topic, the present work outlines a theoretical approach to study this mechanism, specifying testable hypotheses that will allow distinguishing between confronting perspectives, i.e., symbolic accounts that hold that perceptual learning and visual analysis underpin the benefit from HW training vs. embodied sensorimotor accounts that argue for motoric representations as inner part of orthographic representations acquired via HW training. From the evidence critically revisited, we concluded that symbolic accounts are parsimonious and could better explain the benefit from HW training when learning visual graphs. The future challenge will be to put at test the detailed predictions presented here, so that the devil has no longer room in this equation.

From hand to eye: A meta-analysis of the benefit from handwriting training in visual graph recognition

Handwriting (HW) training seems to boost recognition of visual graphs and learning to read more than other learning experiences. However, effects across studies appear to be variable and the underlying cognitive mechanism has been elusive. We thus conducted a meta-analysis on 50 independent experiments (with 1525 participants) to determine the magnitude of this HW benefit in visual graph recognition, while enlightening the underlying cognitive mechanism, by investigating four types of moderators: training program (type of control training, presence/absence of phonological training, and HW tasks adopted); set size and training regime (duration and frequency of training session and total amount of training); granularity of visual discrimination and perceptual learning tasks; and age of participants. The benefit from HW training was moderate-to-large and significant (Hedge’s g = 0.58, SE = .09) and was also modulated by type of control training (larger relative to motor, g = 0.78, than to visual control, g = 0.37), phonological training (larger when it was absent, g = 0.79, than present, g = 0.47), and granularity of visual discrimination (larger for fine-grained, g = 0.93, than coarse-grained, g = 0.19). These results are consistent with symbolic accounts that hold that the advantage from HW training in visual graph recognition is about perceptual learning rather than the motor act. Multiple meta-regressions also revealed that training regime modulated the HW benefit. We conclude that HW training is effective to improve visual graph recognition, and hence, is still relevant for literacy instruction in the present digital era.

Point Visibility Graph Recognition is NP-Hard

Given a 3-SAT formula, a graph can be constructed in polynomial time such that the graph is a point visibility graph if and only if the 3-SAT formula is satisfiable. This reduction establishes that the problem of recognition of point visibility graphs is NP-hard.

Closed graphs are proper interval graphs

Let G be a connected simple graph. We prove that G is a closed graph if and only if G is a proper interval graph. As a consequence we obtain that there exist linear-time algorithms for closed graph recognition.