A Novel Event-Based Incipient Slip Detection Using Dynamic Active-Pixel Vision Sensor (DAVIS)

Abstract

In this paper, a novel approach to detect incipient slip based on the contact area between a transparent silicone medium and different objects using a neuromorphic event-based vision sensor (DAVIS) is proposed. Event-based algorithms are developed to detect incipient slip, slip, stress distribution and object vibration. Thirty-seven experiments were performed on five objects with different sizes, shapes, materials and weights to compare precision and response time of the proposed approach. The proposed approach is validated by using a high speed constitutional camera (1000 FPS). The results indicate that the sensor can detect incipient slippage with an average of 44.1 ms latency in unstructured environment for various objects. It is worth mentioning that the experiments were conducted in an uncontrolled experimental environment, therefore adding high noise levels that affected results significantly. However, eleven of the experiments had a detection latency below 10 ms which shows the capability of this method. The results are very promising and show a high potential of the sensor being used for manipulation applications especially in dynamic environments.

Time-Aggregation-Based Lossless Video Encoding for Neuromorphic Vision Sensor Data

“…Since a single event carries little information and is subject to noise, it is important to process several events to yield a sufficient signal-to-noise-ratio (SNR) for the considered task. Recently several strategies [6], [7], [24], [25], [26], [27], [28], [29] have been proposed that operate on a group of events. These strategies aggregate the information present in the group of events to estimate the solution to the problem.…”

“…Emerging applications of DVS can be found in diverse scenarios ranging from self-driving cars [5], [6] to robotics [7], [8] and drones [9]. Instead of constraining applications to on-board processing many scenarios, such as the coordination of multiple intelligent vehicles (cars, drones, etc.)…”

Ground Truth Force Distribution for Learning-Based Tactile Sensing: A Finite Element Approach

“…One category of optical tactile sensors uses a camera to track sparse markers within a soft, transparent gel, which deforms when subject to external forces, see for example [15], [16]. Other optical devices are able to provide information about the contact with the environment, as shown with the use of dynamic vision sensors [17] and depth cameras [18]. The sensor used here for the evaluation of the proposed approach is based on a standard camera (which retains a small size) that tracks a dense spread of particles within a soft gel, see for example Fig.…”

Dynamic-Vision-Based Force Measurements Using Convolutional Recurrent Neural Networks

“…Neuromorphic vision-based tactile sensing is relatively a new research field which aims to utilizuse event-based cameras to acquire physical properties in the contact area. In the earliest work [25], we proposed a method to utilizuse an event-based camera (Dynamic Vision Sensor) in order to detect incipient slippage using traditional image processing techniques. Similarly, new approaches for slip detection with the DVS are investigated in [26][27][28].…”