Accurate grasp detection learning using oriented regression loss

Purpose Robot automatic grasping has important application value in industrial applications. Recent works have explored on the performance of deep learning for robotic grasp detection. They usually use oriented anchor boxes (OABs) as detection prior and achieve better performance than previous works. However, the parameters of their loss belong to different coordinates, this may affect the regression accuracy. This paper aims to propose an oriented regression loss to solve the problem of inconsistency among the loss parameters. Design/methodology/approach In the oriented loss, the center coordinates errors between the ground truth grasp rectangle and the predicted grasp rectangle rotate to the vertical and horizontal of the OAB. And then the direction error is used as an orientation factor, combining with the errors of the rotated center coordinates, width and height of the predicted grasp rectangle. Findings The proposed oriented regression loss is evaluated on the YOLO-v3 framework to the grasp detection task. It yields state-of-the-art performance with an accuracy of 98.8% and a speed of 71 frames per second with GTX 1080Ti on Cornell datasets. Originality/value This paper proposes an oriented loss to improve the regression accuracy of deep learning for grasp detection. The authors apply the proposed deep grasp network to the visual servo intelligent crane. The experimental result indicates that the approach is accurate and robust enough for real-time grasping applications.

Sensitivity Direction Learning with Neural Networks Using Domain Knowledge as Soft Shape Constraints

If domain knowledge can be integrated as an appropriate constraint, it is highly possible that the generalization performance of a neural network model can be improved. We propose Sensitivity Direction Learning (SDL) for learning about the neural network model with user-specified relationships (e.g., monotonicity, convexity) between each input feature and the output of the model by imposing soft shape constraints which represent domain knowledge. To impose soft shape constraints, SDL uses a novel penalty function, Sensitivity Direction Error (SDE) function, which returns the squared error between coefficients of the approximation curve for each Individual Conditional Expectation plot and coefficient constraints which represent domain knowledge. The effectiveness of our concept was verified by simple experiments. Similar to those such as L2 regularization and dropout, SDL and SDE can be used without changing neural network architecture. We believe our algorithm can be a strong candidate for neural network users who want to incorporate domain knowledge.

Impacts of Stroke on Muscle Perceptions and Relationships with the Motor and Functional Performance of the Lower Extremities

Stroke results in paretic limb disabilities, but few studies have investigated the impacts of stroke on muscle perception deficits in multiaxis movements and related functional changes. Therefore, this study aimed to investigate stroke-related changes in muscle perceptions using a multiaxis ankle haptic interface and analyze their relationships with various functions. Sixteen stroke patients and 22 healthy participants performed active reproduction tests in multiaxis movements involving the tibialis anterior (TA), extensor digitorum longus (EDL), peroneus longus, and flexor digitorum longus (FDL) of the ankle joint. The direction error (DE), absolute error (AE), and variable error (VE) were calculated. The lower extremity of Fugl-Meyer Assessment (FMA-LE), Barthel Index (BI), Postural Assessment Scale for Stroke Patients, Tinetti Performance-Oriented Mobility Assessment (POMA), and 10-m walk test (10MWT) were evaluated. VE of EDL for the paretic ankle was significantly lower than that for the nonparetic ankle (p = 0.009). AE of TA, EDL, and FDL and VE of EDL and FDL of muscle perceptions were significantly lower in healthy participants than in stroke patients (p < 0.05 for both). DE of TA for the paretic ankle was moderately correlated with FMA-LE (r = −0.509) and POMA (r = −0.619) scores. AE and VE of EDL for the paretic ankle were moderately correlated with the 10MWT score (r = 0.515 vs. 0.557). AE of FDL for the paretic ankle was also moderately correlated with BI (r = −0.562). This study indicated poorer accuracy and consistency in muscle perception for paretic ankles, which correlated with lower limb functions of stroke patients.

Adaptive Beamforming for Passive Synthetic Aperture with Uncertain Curvilinear Trajectory

Recently, numerous reconstruction-based adaptive beamformers have been proposed, which can improve the quality of imaging or localization in the application of passive synthetic aperture (PSA) sensing. However, when the trajectory is curvilinear, existing beamformers may not be robust enough to suppress interferences efficiently. To overcome the model mismatch of unknown curvilinear trajectory, this paper presents an adaptive beamforming algorithm by reconstructing the interference-plus-noise covariance matrix (INCM). Using the idea of signal subspace fitting, we construct a joint optimization problem, where the unknown directions of arrival (DOAs) and array shape parameters are coupled together. To tackle this problem, we develop a hybrid optimization method by combining the genetic algorithm and difference-based quasi-Newton method. Then, a set of non-orthogonal bases for signal subspace is estimated with an acceptable computational complexity. Instead of reconstructing the covariance matrix by integrating the spatial spectrum over interference angular sector, we extract the desired signal covariance matrix (DSCM) directly from signal subspace, and then the INCM is reconstructed by eliminating DSCM from the sample covariance matrix (SCM). Numerical simulations demonstrate the robustness of the proposed beamformer in the case of signal direction error, local scattering and random curvilinear trajectory.

Statistical Tracking Behavior Analysis for the Affine Projection Algorithm Based on Direction Error

Under the condition that the step size is less than one, a statistical tracking behavior analysis for the affine projection algorithm based on direction error is discussed. When the unknown true weight vector is modeled by the stochastic walk model, the mean weight error is derived under the four assumptions based on the deterministic recursive equation. Furthermore, the statistical tracking behavior of the steady state is analyzed for the affine projection algorithm based on direction error. Simulation analysis is shown to suppniort the mathematical results.

Relative independence of upper limb position sense and reaching in children with hemiparetic perinatal stroke

Background Studies using clinical measures have suggested that proprioceptive dysfunction is related to motor impairment of the upper extremity following adult stroke. We used robotic technology and clinical measures to assess the relationship between position sense and reaching with the hemiparetic upper limb in children with perinatal stroke. Methods Prospective term-born children with magnetic resonance imaging-confirmed perinatal ischemic stroke and upper extremity deficits were recruited from a population-based cohort. Neurotypical controls were recruited from the community. Participants completed two tasks in the Kinarm robot: arm position-matching (three parameters: variability [Varxy], contraction/expansion [Areaxy], systematic spatial shift [Shiftxy]) and visually guided reaching (five parameters: posture speed [PS], reaction time [RT], initial direction error [IDE], speed maxima count [SMC], movement time [MT]). Additional clinical assessments of sensory (thumb localization test) and motor impairment (Assisting Hand Assessment, Chedoke-McMaster Stroke Assessment) were completed and compared to robotic measures. Results Forty-eight children with stroke (26 arterial, 22 venous, mean age: 12.0 ± 4.0 years) and 145 controls (mean age: 12.8 ± 3.9 years) completed both tasks. Position-matching performance in children with stroke did not correlate with performance on the visually guided reaching task. Robotic sensory and motor measures correlated with only some clinical tests. For example, AHA scores correlated with reaction time (R = − 0.61, p < 0.001), initial direction error (R = − 0.64, p < 0.001), and movement time (R = − 0.62, p < 0.001). Conclusions Robotic technology can quantify complex, discrete aspects of upper limb sensory and motor function in hemiparetic children. Robot-measured deficits in position sense and reaching with the contralesional limb appear to be relatively independent of each other and correlations for both with clinical measures are modest. Knowledge of the relationship between sensory and motor impairment may inform future rehabilitation strategies and improve outcomes for children with hemiparetic cerebral palsy.

Performance Analysis of Linearly arranged Concentric Circular Antenna Array with Low Sidelobe Level and Beamwidth Using Robust Tapering Technique.

In this research, a novel antenna array named Linearly arranged Concentric Circular Antenna Array (LCCAA) is proposed concerning lower beamwidth, lower sidelobe level, sharp ability to detect the false signal, and impressive SINR performance. The performance of the proposed LCCAA beamformer is compared with geometrically identical existing beamformers using the conventional technique where the LCCAA beamformer shows the lowest beamwidth and sidelobe level(SLL) of 12.50°and -15.17 dB in equal element accordingly. However, the performance gets degraded due to looking direction error, and robust techniques- fixed diagonal loading (FDL), optimal diagonal loading (ODL), and variable diagonal loading (VDL) are applied to all the potential arrays to minimize this problem. Furthermore, the LCCAA beamformer is further simulated to reduce the sidelobe applying tapering techniques where the hamming window shows the best performance having 17.097 dB less sidelobe level compared to the uniform window. The proposed structure is also analyzed under a robust tapered (VDL-hamming) method which reduces around 69.92 dB and 48.39 dB more sidelobe level compared to conventional and robust techniques. Analyzing all the performances, it is clear that the proposed LCCAA beamformer is superior and provides the best performance with the proposed robust tapered (VDL-hamming) technique.

Evaluation of Anticipatory Postural Adjustment before Quantified Weight Shifting—System Development and Reliability Test

Anticipatory postural adjustment (APA) existed before a self-induced perturbation is an important motor control skill for balance and gait initiation, but cannot be easily monitored. During proactive balance test, a self-initiated weight shifting is produced. This might be an optimal paradigm for APA measurement. The purpose of this study was to investigate if APAs existed in the proactive balance test which consists of quantifiable weight shifting. The feature and reliability of the APAs were also evaluated. We firstly built a proactive balance test program on the commercially available Wii balance board. The program could generate adjustable target direction and distance for guiding subjects performing quantifiable weight shifting. The center of pressure (COP) was recorded and analyzed for balance-related variables (path length, path time, and direction error) and APA-related variables (APA time, APA distance, and APA correction). The results showed that APAs could be detected in every testing trial. Adequate to good reliability in both balance and APA-related variables were found. This study proved the feasibility of quantifying APA during proactive balance tests and its feasibility for clinical- and home-based measurements.

Szemmozgások elemzése tradicionális és újszerű vizuális tesztkörnyezetben: a háttérkép disztraktor hatása a szakkádikus paraméterekre

Háttér és célkitűzésekA szakkádikus szemmozgási paraméterek biomarkerként történő önálló használata egyes degeneratív neuropszhichiátriai kórképek felismerésében egyelőre kérdéses. Jelen vizsgálatunk célkitűzése egy olyan szakkádikus szemmozgásvizsgálati protokoll megvalósítása, amely a nemzetközi klinikai kutatásoknak megfelelően kialakított vizsgálati paraméterekkel jellemezhető. Továbbá egészséges vizsgált személyek szakkádparamétereinek a nemzetközileg publikált adatokkal való összehasonlítása, illetve a Boston Sütilopás feladatban használt kép vizuális tesztkörnyezetbe történő beépítésének disztraktor-hatásvizsgálata a szakkádikus paraméterekre.MódszerVizsgálatainkat egészséges önkéntes alanyokon végeztük Tobii Pro X3-120 berendezéssel, két eltérő vizuális környezetet tartalmazó, egyéb tekintetben teljesen megegyező felépítésű, proszakkád és antiszakkád tesztek gap és overlap feladataiban. Az egyik csoport vizuális tesztkörnyezete standard szürke háttérből és fekete stimulusokból állt (STD tesztcsoport), a másiké a Boston Afázia Teszt Sütilopás képleírási feladatban használt képet és zöld-piros színű stimulusokat tartalmazott (BSL tesztcsoport).EredményekA proszakkád és antiszakkád overlap latencia mindkét csoportban nagyobb volt, mint a gap feladatban. A vizsgálati alanyok életkora közepes erősségű módon korrelált az STD csoport proszakkád gap latenciájával, illetve a BSL csoport proszakkád overlap latencia, antiszakkád gap/overlap latencia és overlap időtartam értékével. A csoportok közötti életkori eltérés statisztikai kontrollja mellett nem találtunk különbséget a proszakkád és antiszakkád latencia, illetve csúcssebesség tekintetében. A szakkád időtartamok szignifi kánsan rövidebbek voltak a BSL csoportban. Az iránytévesztési ráta a proszakkád tesztben megegyezett; az antiszakkád gap időtartam, az overlap időtartam, illetve a gap iránytévesztési ráta szignifi káns csoportkülönbséget mutatott.KövetkeztetésekA nemzetközi sztenderdeknek megfelelő újszerű vizsgálati protokoll alkalmasnak látszik hagyományos neuropszichológiai tesztekkel és kutatócsoportunk közelmúltban kidolgozott automatikus beszédfelismerő algoritmusokat alkalmazó tesztjeivel kombinálva egészséges és demencia szindrómával élő személyek multimodális klinikai vizsgálatában történő felhasználásra.Background and aimsThe use of saccadic parameters as specifi c biomarkers in the diagnosis of degenerative neuropsychiatric disorders is still problematic. The aim of the current study was to 1) establish a protocol for saccadic eye movement measurements that is concordant with international clinical investigations; 2) compare saccadic parameters of healthy subjects with internationally published data, and 3) integrate the picture from Boston Cookie Theft test into the visual test environment and evaluate its distractor effects on saccadic parameters.MethodsHealthy volunteers were assessed with Tobii Pro X3-120 eye tracker in two distinct visual settings, but otherwise identical test environment evaluating prosaccades and antisaccades in gap and overlap conditions. One group was assessed in a visual test environment based on a traditional uniform grey background with black stimuli (STD test group), while the visual test environment of the other group contained the Cookie Theft picture of the Boston Diagnostic Aphasia Examination with green and red stimuli (BSL group).ResultsProsaccade and antisaccade latencies were signifi cantly longer in the overlap condition both in the BSL and STD groups. After controlling for age, the STD and BSL group did not differ in terms of prosaccade latency, antisaccade latency or peak velocity; only saccade durations were shorter in the BSL group. Saccadic direction error rate in the prosaccade task was identical in both groups, while the antisaccade gap duration, overlap duration and gap direction error rates showed signifi cant group differences.The present, newly developed protocol conforms to international standards, and may be useful for multi-modal clinical studies assessing healthy subjects and people suffering from dementia, combined with traditional neuropsychological tasks and the speech recognition task recently developed by our research group.

An Improved Augmented Algorithm for Direction Error in XPNAV

Recently, X-ray pulsar-based navigation (XPNAV) as a significant navigation method has been widely used in deep space exploration. However, the accuracy of XPNAV is limited to the existence of the pulsar direction error. To improve the performance of XPNAV, we have proposed a novel algorithm named “the modified augmented state extended Kalman filter” (MASEKF). The algorithm considers the high-order terms of direction error and then adds a more precise direction error into state equation and measurement equation. In the simulation, by comparing the performance of MASEKF, EKF, and ASEKF at the same time, it is found that MASEKF has better performance in the accuracy and stability, and the results also demonstrate that MASEKF algorithm has faster convergence speed. This paper provides a strong reference for other improvements of algorithms towards direction error. The purpose of this study is to establish MASEKF and add the direction error into the measurement equation and the state equation, so as to realize the coordination and symmetry of the algorithm.