A convolution neural network based semi-parametric dynamic model for industrial robot

Robot dynamic model is widely applied to control, collision detection and motion planning. Accurate dynamic model can achieve better performance for the above applications. Traditional dynamic models have several limitations, such as the complex hypotheses for friction model and the requirement of additional joint torque sensors. This article constructs a convolution neural network (CNN) based semi-parametric dynamic (SPD) model by only using the motor encoder signals and motor currents. The SPD model not only contains the physically feasible parameters but also compensates the dynamic model by CNN. The parametric and non-parametric parts constitute the SPD model. A lightweight CNN is proposed to simultaneously ensure the accuracy and computational efficiency. To effectively train the CNN model, a dataset generation method, which expands the excitation trajectory and only uses a continuous trajectory to record data, is proposed. The CNN-based SPD model is verified on a 6-DoF laboratory-developed industrial robot only with the proprioceptive sensors. Compared with the traditional rigid body dynamics (RBD) model, the average error of the CNN-based SPD model is reduced by 9.23% in terms of the experimental results. Meanwhile, the proposed CNN-based method achieves better performance than other supervised methods.

A Factor-Graph-Based Approach to Vehicle Sideslip Angle Estimation

Sideslip angle is an important variable for understanding and monitoring vehicle dynamics, but there is currently no inexpensive method for its direct measurement. Therefore, it is typically estimated from proprioceptive sensors onboard using filtering methods from the family of the Kalman filter. As a novel alternative, this work proposes modeling the problem directly as a graphical model (factor graph), which can then be optimized using a variety of methods, such as whole-dataset batch optimization for offline processing or fixed-lag smoothing for on-line operation. Experimental results on real vehicle datasets validate the proposal, demonstrating a good agreement between estimated and actual sideslip angle, showing similar performance to state-of-the-art methods but with a greater potential for future extensions due to the more flexible mathematical framework. An open-source implementation of the proposed framework has been made available online.

Practical Aspects of Model-Based Collision Detection

Recently, with the increased number of robots entering numerous manufacturing fields, a considerable wealth of literature has appeared on the theme of physical human-robot interaction using data from proprioceptive sensors (motor or/and load side encoders). Most of the studies have then the accurate dynamic model of a robot for granted. In practice, however, model identification and observer design proceeds collision detection. To the best of our knowledge, no previous study has systematically investigated each aspect underlying physical human-robot interaction and the relationship between those aspects. In this paper, we bridge this gap by first reviewing the literature on model identification, disturbance estimation and collision detection, and discussing the relationship between the three, then by examining the practical sides of model-based collision detection on a case study conducted on UR10e. We show that the model identification step is critical for accurate collision detection, while the choice of the observer should be mostly based on computation time and the simplicity and flexibility of tuning. It is hoped that this study can serve as a roadmap to equip industrial robots with basic physical human-robot interaction capabilities.

Information Fusion of GPS, INS and Odometer Sensors for Improving Localization Accuracy of Mobile Robots in Indoor and Outdoor Applications

SUMMARY In mobile robot localization with multiple sensors, myriad problems arise as a result of inadequacies associated with each of the individual sensors. In such cases, methodologies built upon the concept of multisensor fusion are well-known to provide optimal solutions and overcome issues such as sensor nonlinearities and uncertainties. Artificial neural networks and fuzzy logic (FL) approaches can effectively model sensors with unknown nonlinearities and uncertainties. In this article, a robust approach for localization (positioning) of a mobile robot in indoor as well as outdoor environments is proposed. The neural network is utilized as a pseudo-sensor that models the global positioning system (GPS) and is used to predict the robot’s position in case of GPS signal loss in indoor environments. The data from proprioceptive sensors such as inertial sensors and GPS are fused using the Kalman and the complementary filter-based fusion schemes in the outdoor case. To eliminate the position inaccuracies due to wheel slippage, an expert FL system (FLS) is implemented and cascaded with the sensor fusion module. The proposed technique is tested both in simulation and in real scenarios of robot movements. The simulations and results from the experimental platform validate the efficacy of the proposed algorithm.

Vision for Robust Robot Manipulation

Advances in Robotics are leading to a new generation of assistant robots working in ordinary, domestic settings. This evolution raises new challenges in the tasks to be accomplished by the robots. This is the case for object manipulation where the detect-approach-grasp loop requires a robust recovery stage, especially when the held object slides. Several proprioceptive sensors have been developed in the last decades, such as tactile sensors or contact switches, that can be used for that purpose; nevertheless, their implementation may considerably restrict the gripper’s flexibility and functionality, increasing their cost and complexity. Alternatively, vision can be used since it is an undoubtedly rich source of information, and in particular, depth vision sensors. We present an approach based on depth cameras to robustly evaluate the manipulation success, continuously reporting about any object loss and, consequently, allowing it to robustly recover from this situation. For that, a Lab-colour segmentation allows the robot to identify potential robot manipulators in the image. Then, the depth information is used to detect any edge resulting from two-object contact. The combination of those techniques allows the robot to accurately detect the presence or absence of contact points between the robot manipulator and a held object. An experimental evaluation in realistic indoor environments supports our approach.

An acoustic-based approach for real-time deep-water navigation of an AUV

Navigation of Autonomous Underwater Vehicles (AUVs) remains a challenge due to the impossibility to use radio frequency signals and Global Positioning System (GPS). Navigation systems usually integrate different proprioceptive sensors to estimate the asset and the speed of the vehicle. In particular, the Doppler Velocity Log (DVL) is fundamental during the navigation to have an accurate estimate of the vehicle’s speed. This work addresses the enhancement of the navigation performance of an AUV through the development of a Deep Water Navigation Filter (DWNF). The DWNF is able to work in those scenarios where traditional navigation sensors show their limits: e.g., deep waters where DVL bottom lock cannot be achieved, or areas where the use of traditionally used static and dedicated beacons is incompatible with the mission requirements. The proposed approach exploits the concept of using a network of vehicles cooperatively supporting each other for their navigation. Several types of measurements coming from the different nodes (i.e. acoustic positioning system such as ship-mounted SSBL acoustic positioning system, USBL, range measurements from the different nodes) are fused in an Extended Kalman Filter framework with the odometry data. DWNF pushes forward the idea of using a network of robotic assets as a provider of navigation services allowing more flexible and robust operations of the deployed system. The approach has been tested at sea during several experiments. We report here results from DWNF running successfully in real-time on the NATO STO-Centre for Maritime Research and Experimentation (CMRE) vehicles during the Dynamic Mongoose’17 experimentation off the South coast of Iceland (June-July 2017).