Object recognition in containers is extremely difficult for robots. Dynamic audio signals are more responsive to an object's internal property. Therefore, we adopt the dynamic contact method to collect acoustic signals in the container and recognize objects in containers. Traditional machine learning is to recognize objects in a closed environment, which is not in line with practical applications. In real life, exploring objects is dynamically changing, so it is necessary to develop methods that can recognize all classes of objects in an open environment. A framework for recognizing objects in containers using acoustic signals in an open environment is proposed, and then the kernel k nearest neighbor algorithm in an open environment (OSKKNN) is set. An acoustic dataset is collected, and the feasibility of the method is verified on the dataset, which greatly promotes the recognition of objects in an open environment. And it also proves that the use of acoustic to recognize objects in containers has good value.

Tactile information is valuable in determining properties of objects that are inaccessible from visual perception. A new type of tangential friction and normal contact force magnetostrictive tactile sensor was developed based on the inverse magnetostrictive effect, and the force output model has been established. It can measure the exerted force in the range of 0–4 N, and it has a good response to the dynamic force in cycles of 0.25–0.5 s. We present a tactile perception strategy that a manipulator with tactile sensors in its grippers manipulates an object to measure a set of tactile features. It shows that tactile sensing system can use these features and the extreme learning machine algorithm to recognize household objects—purely from tactile sensing—from a small training set. The complex matrixes show the recognition rate is up to 83%.