Search

Aiming at the problems of low multi-scale detection accuracy, missed detection and false detection of road scene targets, a lightweight YOLOv7-Tiny algorithm that integrates polarization self-attention mechanism is proposed. First, the bounding box position loss function in the algorithm is replaced by It is the α-CIoU loss function to improve the convergence accuracy; secondly, the polarization self-attention mechanism is introduced into the path aggregation network to enhance the information expression of the region of interest; finally, the training set is preprocessed, and the grayscale world is used for data enhancement. The algorithm reduces the influence of different lighting conditions on the real color performance of the object and improves the detection accuracy. Compared with the original algorithm, the performance of the improved algorithm in the road target recognition task of the KITTI dataset is significantly improved compared with the original algorithm; mAP, Precision and Recall increased by 3.2%, 0.25% and 3.64% respectively, and the robustness and generalization ability are better. [ABSTRACT FROM AUTHOR]

An intelligent system for spatial visual feedback is presented, which enables the robot's autonomy for a range of robotic assembly tasks, in particular for arc welding, in an unstructured and "fixtureless" environment. The robot's autonomy is empowered by an embedded inductive inference-based machine learning module which learns a welded object's structural properties in the form of geometrical properties. In particular, the system tries to recognize line segments, using a spatial (three-dimensional) visual sensor in order to autonomously execute the objective task. The innovative result is that the recognition of the geometric primitives is done without a predefined Computer-Aided Design (CAD) model, significantly improving the system's autonomy and robustness. The system is validated on real-world welding tasks. [ABSTRACT FROM AUTHOR]

We present a tactile telepresence system for real-time transmission of information about object stiffness to the human fingertips. Experimental tests were performed across two laboratories (Italy and Ireland). In the Italian laboratory, a mechatronic sensing platform indented different rubber samples. Information about rubber stiffness was converted into on-off events using a neuronal spiking model and sent to a vibrotactile glove in the Irish laboratory. Participants discriminated the variation of the stiffness of stimuli according to a two-alternative forced choice protocol. Stiffness discrimination was based on the variation of the temporal pattern of spikes generated during the indentation of the rubber samples. The results suggest that vibrotactile stimulation can effectively simulate surface stiffness when using neuronal spiking models to trigger vibrations in the haptic interface. Specifically, fractional variations of stiffness down to 0.67 were significantly discriminated with the developed neuromorphic haptic interface. This is a performance comparable, though slightly worse, to the threshold obtained in a benchmark experiment evaluating the same set of stimuli naturally with the own hand. Our paper presents a bioinspired method for delivering sensory feedback about object properties to human skin based on contingency-mimetic neuronal models, and can be useful for the design of high performance haptic devices. [ABSTRACT FROM AUTHOR]

This two-part paper presents an approach to the control of robot endpoint compliance, i.e., elasto-mechanical interaction between a robot and its environment using kinematic redundancy instead of actuation redundancy. In Part I this approach is developed by proposing the Configuration-based Stiffness Control (CSC) method for kinetostatically consistent control of robot compliant behaviour, based on the gradient projection of the cost function which minimizes the norm of off-diagonal elements of the jointspace matrix. In Part II validity of the proposed compliance control method is tested by simulation experiments using as a simulation platform two specific cases of most simple kinematically redundant robot arms: Case 1 -- experiments with onedimensional taskspace (m=1) and minimal possible redundancy, r = (n -- m) = 1, and Case 2 -- experiments with onedimensional taskspace (m=1) and minimal possible hyper-redundancy, r = 2 and r > m. In both cases the singularity and joint limits were not considered. [ABSTRACT FROM AUTHOR]

When the robot endpoint compliance is dominantly influenced by the flexibility of its joints, the robot taskspace generalized stiffness matrix can be mapped onto jointspace using appropriate congruence transformation. Thus produced, the jointspace stiffness matrix is generally nondiagonal. Off-diagonal elements can be generated by redundant actuation only (polyarticular actuators). Although this kind of actuation is widely present in biological systems, its practical implementation in engineering systems is very difficult. To overcome this problem, use of kinematic redundancy is proposed. This two-part paper presents an approach to the control of robot endpoint compliance, i.e., elasto-mechanical interaction between a robot and its environment using kinematic redundancy instead of actuation redundancy. In Part I this approach is developed by proposing the Configuration-based Stiffness Control (CSC) method for kinetostatically consistent control of robot compliant behaviour, based on the gradient projection of the cost function which minimizes the norm of off-diagonal elements of the jointspace matrix. [ABSTRACT FROM AUTHOR]