Proprioceptive slip detection and state estimation of multi-legged robots in slippery scenarios

A novel gait and slip detection algorithm for walking robots using an inertial measurement unit was developed. An unscented Kalman filter was formulated with a simple dynamic model as a block on a slope without translations. Considerable prediction errors resulted when unmodeled dynamics (i.e., translation) occurred. These prediction errors were used in a binary Bayes filter to estimate the probability of gait and slip states. A proof of concept experiment was conducted with a monopedal walker under three floor conditions (nonslip, poly, and poly-oil) and three orientations (flat, uphill, and downhill). Realtime and offline detection at 100 Hz were successful. Continuous gait cycles were detected in proper order. Slip detection was successful except for very mild slips involving small jerk. The proposed algorithm provided a robust gait and slip detection method with a single set of parameters without knowledge of floor conditions and inclinations.

Slip detection in robotic grasping constitutes a critical technology for ensuring stable manipulation. However, current methodologies predominantly rely on single sensing modalities while neglecting temporal correlations in multi-source data, resulting in limited generalization capabilities under complex scenarios. To address this limitation, this paper proposes a multi-modal visual-tactile fusion network for slip detection, which achieves cross-modal feature complementarity and robust slip state discrimination through coordinated temporal learning of 2D visual, point cloud, and tactile data features. To validate the method’s effectiveness, we constructed a visual-tactile dataset incorporating 2D visual, point cloud, and tactile information. The proposed model achieves a slip detection precision of 96.02% on this dataset. Furthermore, comparative experiments with baseline algorithms under varying illumination conditions demonstrate that our model maintains detection precisions of 90.52% and 85.74% in overexposed and dynamic lighting environments, respectively, outperforming baseline models. Additional robustness evaluations under occlusion environment and grasping postures confirm the model’s superior performance compared to single-modality approaches. Moreover, the proposed method demonstrates excellent performance in practical grasping experiments. These results substantiate that the proposed model can accurately determine object slip states even when confronted with missing 2D visual data, incomplete point cloud information, or degraded tactile sensor data quality, thereby providing a reliable perceptual solution for dexterous robotic manipulation.

Robots with multi-sensors always have a problem of weak pairing among different modals of the collected information produced by multi-sensors, which leads to a bad perception performance during robot interaction. To solve this problem, this paper proposes a Force Vision Sight (FVSight) sensor, which utilizes a distributed flexible tactile sensing array integrated with a vision unit. This innovative approach aims to enhance the overall perceptual capabilities for object recognition. The core idea is using one perceptual layer to trigger both tactile images and force-tactile arrays. It allows the two heterogeneous tactile modal information to be consistent in the temporal and spatial dimensions, thus solving the problem of weak pairing between visual and tactile data. Two experiments are specially designed, namely object classification and slip detection. A dataset containing 27 objects with deep presses and shallow presses is collected for classification, and then 20 slip experiments on three objects are conducted. The determination of slip and stationary state is accurately obtained by covariance operation on the tactile data. The experimental results show the reliability of generated multimodal data and the effectiveness of our proposed FVSight sensor.

A new method to measure the complexity of time series is presented — fuzzy entropy algorithm (FuzzyEn). Firstly, the adhesion mechanism and the traditional methods of slip detection are introduced. Then, the principle of fuzzy entropy algorithm is described. At last, the algorithm is applied to measure the complexity of locomotive speed signal. As the experimental data showed, the proposed method can effectively identify the slip state of locomotive. Compared with the traditional methods, it can detect the slip state of the locomotive in advance.

Existing gripping devices limit the way of gripping the object, and the object may slide due to insufficient friction, when the manipulator grips the object, the object may slip phenomenon, which leads to the manipulator can not complete the gripping work normally. In order to solve this problem, this paper proposes a robotic slipping sensor to detect the slipping state of the object and its slipping distance, the sensor through the friction of two different materials and electrostatic induction phenomenon of triboelectricity and the peak voltage signal to determine whether the contact object produces the phenomenon of slipping and its slipping distance. This design integrates two rectangular copper foils and two polytetrafluoroethylene (PTFE) films together to form a triboelectricity nanogenerator in independent layer mode, which judges the slip distance of an object by the peak voltage signal generated by the object’s slip, which is flexible and can be combined with a robot to make the robot more flexible and convenient in its work. In order to verify the performance of this sensor, horizontal slip test and vertical slip test were conducted. In the horizontal slip test and vertical slip test, the peak voltage signal output from the TENG sensor has a linear relationship with the slip distance of the object. The sensor and the object contact slip process ends after 100 ms, the oscilloscope will output the peak voltage signal, so that according to the size of the peak voltage signal to determine the object in the range of 0–10 cm slip distance, for judging whether the object appears to slip phenomenon and the occurrence of the phenomenon of the slip distance it produces provides a flexible program.