Video anomaly detection (VAD) has long been studied as a crucial problem in public security and crime prevention. In recent years, weakly-supervised VAD (WVAD) has attracted considerable attention due to their easy annotation process and promising research results. While existing WVAD methods mainly tackle static datasets, the possibility that the domain of data can vary has been neglected. To adapt such domain shift, the continual learning (CL) perspective is required because otherwise additional training using only newly incoming data could easily cause performance degradation for previous data, i.e., forgetting. Therefore, we propose a brand-new approach, called Continual Anomaly Detection with Ensembles (CADE) that is the first work combining CL and WVAD viewpoints. Specifically, CADE uses the Dual-Generator (DG) to address data imbalance and label uncertainty in WVAD. We also found that forgetting exacerbates the "incompleteness" where the model becomes biased towards certain anomaly modes, leading to missed detections of various anomalies. To address this, we propose a Multi-Discriminator (MD) ensemble that captures missed anomalies in past scenes due to forgetting, using multiple models. Extensive experiments show that CADE significantly outperforms existing VAD methods on the common multi-scene VAD datasets, such as the ShanghaiTech, UCF-Crime, and Charlotte Anomaly Dataset.

In this paper, we propose an office layout support system using interactive genetic algorithm. In the proposed system, some conditions such as size and form of room, size and position of window and door, and the number of desks, shelves and printers and so on are given by users, some layout plans which satisfy the conditions are generated by genetic algorithm. In this system, desks are packed per group, and relation between arrangement plans for every group is expressed in the sequence-pair representation. We carried out a series of computer experiments in order to demonstrate the effectiveness of the proposed system and confirmed that the proposed system can generate various layout plans.

In this paper, we propose an office layout support system using island model genetic algorithm. In the proposed system, some conditions such as size and form of room, size and position of window and door, and the number of desks, shelves and printers and so on are given by users, some layout plans which satisfy the conditions are generated by genetic algorithm. In this system, desks are packed per group, and relation between arrangement plans for every group is expressed in the sequence-pair representation. We carried out a series of computer experiments in order to demonstrate the effectiveness of the proposed system

A new concept of the human-robots collaboration is introduced in this system; the task is shared among the human and the robots. The robots appropriately deform and support the object, so that the human can easily handle it by only applying his/her intentional force to the object. First, the controller of multiple robots is designed so as to decrease the effect of noises from force sensors. Then deformation control of the flexible object is designed using the internal force applied to the object. The control system is experimentally implemented in a dual manipulator system which consists of two industrial robots. The experimental results illustrate the concept of the system.

In this paper, we discuss a problem relating to the force/moment transformation for the handling a large object by multiple robots in coordination. Three control algorithms, based on impedance control of each manipulator, are then proposed so as to lessen the effect of the transformation. The algorithms are implemented in dual manipulator system, which consists of two industrial robots. Experimental results illustrate the validity of the proposed control algorithms.