Reinforcement Learning Path Planning Method with Error Estimation

Path planning is often considered as an important task in autonomous driving applications. Current planning method only concerns the knowledge of robot kinematics, however, in GPS denied environments, the robot odometry sensor often causes accumulated error. To address this problem, an improved path planning algorithm is proposed based on reinforcement learning method, which also calculates the characteristics of the cumulated error during the planning procedure. The cumulative error path is calculated by the map with convex target processing, while modifying the algorithm reward and punishment parameters based on the error estimation strategy. To verify the proposed approach, simulation experiments exhibited that the algorithm effectively avoid the error drift in path planning.

Analysis, Evaluation and Exact Tracking of the Finite Precision Error Generated in Arbitrary Number of Multiplications

In the present paper, a novel approach is introduced for the study, estimation and exact tracking of the finite precision error generated and accumulated during any number of multiplications. It is shown that, as a rule, this operation is very “toxic”, in the sense that it may force the finite precision error accumulation to grow arbitrarily large, under specific conditions that are fully described here. First, an ensemble of definitions of general applicability is given for the rigorous determination of the number of erroneous digits accumulated in any quantity of an arbitrary algorithm. Next, the exact number of erroneous digits produced in a single multiplication is given as a function of the involved operands, together with formulae offering the corresponding probabilities. In case the statistical properties of these operands are known, exact evaluation of the aforementioned probabilities takes place. Subsequently, the statistical properties of the accumulated finite precision error during any number of successive multiplications are explicitly analyzed. A method for exact tracking of this accumulated error is presented, together with associated theorems. Moreover, numerous dedicated experiments are developed and the corresponding results that fully support the theoretical analysis are given. Eventually, a number of important, probable and possible applications is proposed, where all of them are based on the methodology and the results introduced in the present work. The proposed methodology is expandable, so as to tackle the round-off error analysis in all arithmetic operations.

The method for identifying of inaccuracy causes in turning machining center by processing a sample part

The article discusses the issues of the processing method of a turning machining center for processing the accuracy of processing a sample part. The model of sample part with the smallest possible control surfaces processed by various shaping methods has been developed to detect the amount of machine errors, such as the accumulated error of the screw pitch, or the axial non-perpendicularity, or the misalignment of the X and Y drives. This allows you to get more complete information of the equipment accuracy. A test procedure is presented according to the results of measuring each surface of the sample part

Tensegrity Structures Incorporating Actuator and Pseudoelastic Shape Memory Alloys

Tensegrity structures are networks of tensile and compressive truss members that have pre-stressability and shape-morphing capabilities. Potential applications of tensegrities in the aerospace, civil, and robotics fields require them to have actuation capabilities and adjustable stiffness. An approach to infuse these properties into tensegrities is to employ active materials. Shape memory alloys (SMAs) are active materials with the ability of exchanging mechanical and thermal energies. They have actuation capabilities enabled by the shape memory effect and large recoverable deformations enabled by the pseudoelastic effect. This paper presents a study on the integration of actuator and pseudoelastic SMAs into tensegrities to create a new class of stifftruss structures that exhibit controlled large deformations. A model for tensegrities that incorporates mechanical equilibrium, thermal equilibrium, and an SMA constitutive model is first developed. The tensile members in the tensegrities may be comprised of actuator or pseudoelastic SMA wires. The actuator wires can be manipulated through Joule heating to change the shape of the tensegrity structure on demand. The pseudoelastic wires provide high stiffness under moderate external disturbances, and become compliant and allow for large deformations as their stress is increased by the actuator wires. This unique combination of actuator and pseudoelastic SMA members in tensegrities is demonstrated through examples of controlled morphing of a tensegrity beam and a tensegrity plate. The results show that using pseudoelastic members antagonistic to the actuators, as opposed to elastic members, reduces the accumulated error and the energy required to control the tensegrities.

Landmark navigation in a mantis shrimp

Mantis shrimp commonly occupy burrows in shallow, tropical waters. These habitats are often structurally complex where many potential landmarks are available. Mantis shrimp of the species Neogonodactylus oerstedii return to their burrows between foraging excursions using path integration, a vector-based navigational strategy that is prone to accumulated error. Here, we show that N. oerstedii can navigate using landmarks in parallel with their path integration system, correcting for positional uncertainty generated when navigating using solely path integration. We also report that when the path integration and landmark navigation systems are placed in conflict, N. oerstedii will orientate using either system or even switch systems enroute. How they make the decision to trust one navigational system over another is unclear. These findings add to our understanding of the refined navigational toolkit N. oerstedii relies upon to efficiently navigate back to its burrow, complementing its robust, yet error prone, path integration system with landmark guidance.

Cross-denoising Network against Corrupted Labels in Medical Image Segmentation with Domain Shift

Deep convolutional neural networks (DCNNs) have contributed many breakthroughs in segmentation tasks, especially in the field of medical imaging. However, domain shift and corrupted annotations, which are two common problems in medical imaging, dramatically degrade the performance of DCNNs in practice. In this paper, we propose a novel robust cross-denoising framework using two peer networks to address domain shift and corrupted label problems with a peer-review strategy. Specifically, each network performs as a mentor, mutually supervised to learn from reliable samples selected by the peer network to combat with corrupted labels. In addition, a noise-tolerant loss is proposed to encourage the network to capture the key location and filter the discrepancy under various noise-contaminant labels. To further reduce the accumulated error, we introduce a class-imbalanced cross learning using most confident predictions at class-level. Experimental results on REFUGE and Drishti-GS datasets for optic disc (OD) and optic cup (OC) segmentation demonstrate the superior performance of our proposed approach to the state-of-the-art methods.

Landmark navigation in a mantis shrimp

SummaryMantis shrimp are predatory crustaceans that commonly occupy burrows in shallow, tropical waters worldwide. Most of these animals inhabit structurally complex, benthic environments where many potential landmarks are available. Mantis shrimp of the species Neogonodactylus oerstedii return to their burrows between foraging excursions using path integration, a vector-based navigational strategy that is prone to accumulated error. Here we show that N. oerstedii can navigate using landmarks in parallel with their path integration system, offseting error generated when navigating using solely path integration. We also report that when the path integration and landmark navigation systems are placed in conflict, N. oerstedii will orient using either system or even switch systems enroute. How they make the decision to trust one navigational system over another is unclear. These findings add to our understanding of the refined navigational toolkit N. oerstedii relies upon to efficiently navigate back to its burrow, complementing its robust, yet error prone, path integration system with landmark guidance.

Path integration error and adaptable search behaviors in a mantis shrimp

Mantis shrimp of the species Neogonodactylus oerstedii occupy small burrows in shallow waters throughout the Caribbean. These animals use path integration, a vector-based navigation strategy, to return to their homes while foraging. Here we report that path integration in N. oerstedii is prone to error accumulated during outward foraging paths and we describe the search behavior that N. oerstedii employs after it fails to locate its home following the route provided by its path integrator. This search behavior forms continuously expanding, non-oriented loops that are centered near the point of search initiation. The radius of this search is apparently scaled to the animal’s accumulated error during path integration, improving the effectiveness of the search. The search behaviors exhibited by N. oerstedii bear a striking resemblance to search behaviors in other animals, offering potential avenues for the comparative examination of search behaviors and how they are optimized in disparate taxa.Summary StatementMantis shrimp use path integration, an error-prone navigational strategy, when travelling home. When path integration fails, mantis shrimp employ a stereotyped yet flexible search pattern to locate their homes.

Enhanced Heuristic Drift Elimination with Adaptive Zero-Velocity Detection and Heading Correction Algorithms for Pedestrian Navigation

As pedestrian dead-reckoning (PDR), based on foot-mounted inertial sensors, suffers from accumulated error in velocity and heading, an improved heuristic drift elimination (iHDE) with a zero-velocity update (ZUPT) algorithm was proposed for simultaneously reducing the error in heading and velocity in complex paths, i.e., with pathways oriented at 45°, curved corridors, and wide areas. However, the iHDE algorithm does not consider the changes in pedestrian movement modes, and it can deteriorate when a pedestrian walks along a straight path without a pre-defined dominant direction. To solve these two problems, we propose enhanced heuristic drift elimination (eHDE) with an adaptive zero-velocity update (AZUPT) algorithm and novel heading correction algorithm. The relationships between the magnitude peaks of the y-axis angular rate and the detection thresholds were established only using the readings of the three-axis accelerometer and the three-axis gyroscopic, and a mechanism for constructing temporary dominant directions in real time was introduced. Real experiments were performed and the results showed that the proposed algorithm can improve the still-phase detection accuracy of a pedestrian at different movement motions and outperforms the iHDE algorithm in complex paths with many straight features.