Recent technology and market trends have demanded the significant need for feasible solutions to video/camera systems analytics. This paper provides a comprehensive account on theory application of intelligent video It highlights system architectures, tasks, related analytic methods. clearly demonstrates that importance role analytics play can be found in variety domains such as transportation surveillance. Research directions are outlined with focus what is essential achieve goals

This paper deals with a fuzzy-based intelligent robotic system that requires various capabilities normally associated intelligence. It acquires skills and knowledge through interaction dynamic environment. Subsumption architectures, behavior-based artificial intelligence, behavioral engineering for systems have been discussed as new technologies systems. proposes "structured intelligence". We focus on mobile fuzzy controller propose sensory network allows the robot to perceive its An...

This paper proposes the control system for 3-D locomotion of a humanoid biped robot based on biological approach. The muscular in human body and neural oscillator generating signals are adapted this paper. We extend neuro-locomotion modeling multiple neuron system, where motoric neurons represent sensoric sensor inside body. output from coupled representing angle joint level controlled by gain that energy burst driving each motor. direction length step can be adjusted command neurons. In...

Activity recognition which aims to accurately distinguish human actions in complex environments plays a key role human-robot/computer interaction. However, long-lasting and similar will cause poor feature sequence extraction thus lead reduction of the accuracy. We propose novel discriminative deep model (D3D-LSTM) based on 3D-CNN LSTM for both single-target interaction action improve spatiotemporal processing performance. Our models have several notable properties: 1) A real-time fusion...

This paper proposes a localization method using multiresolution maps for the navigation of multiple mobile robots based on formation behaviors. The remote control is one most important tasks in robotics to realize distributed monitoring unknown and/or dynamic environments. However, it very difficult human operator separately at same time. Therefore, autonomous behaviors are required reduce mental and physical loads operator. If each robot can estimate self-position or relative position...

This paper proposes a human localization method in informationally structured space based on sensor network First, we explain space, robot partners, and networks developed this study. Next, apply fuzzy spiking neural to extract person from the measured data by network. Furthermore, propose learning of time series data. Finally, discuss effectiveness proposed methods through experimental results living room.

This article examines the importance of integrating locomotion and cognitive information for achieving dynamic from a viewpoint combining biology ecological psychology. We present mammalian neuromusculoskeletal model external sensory processing to muscle activation, which includes: 1) visual-attention control mechanism controlling attention inputs; 2) object recognition representing primary motor cortex; 3) that determines commands traveling down corticospinal reticulospinal tracts; 4)...

Recently, the rate of elderly people rises in super-aging society. Human-friendly robots can be used to support mental and physical care for assist caregivers people. Robotic conversation activate brain such improve their concentration memory abilities. However, it is difficult a robot converse appropriately with person even if many contents are designed advance because performance voice recognition not enough daily conversation. Recognition human gestures also important order perform smooth...

There are currently many quadruped robots suited to a wide range of applications, but traversing some terrains, such as vertical ladders, remains an open challenge. is still need develop adaptive that can walk and climb efficiently. This paper presents robot that, by mimicking feline structure, supports several novel capabilities. We design paw structure point-cloud-based sensory structures incorporating quad-composite time-of-flight sensor dual-laser finder. The proposed equipped with...

Development of human skeleton tracking requires high accuracy with affordable installation to enlarge their applicability. This paper proposes using multiple cameras minimize occlusion. We combined modules from Azure based on ONNX Runtime. Each module uses passive infrared as the segmentation and recognition process depth information transform 3D position. module's output data is separated into six parts: right-upper limb, left-upper right-lower left-lower head, torso. Then those part...

Translating human intent into robot commands is crucial for the future of service robots in an aging society. Existing Human-Robot Interaction (HRI) systems relying on gestures or verbal are impractical elderly due to difficulties with complex syntax sign language. To address challenge, this paper introduces a multi-modal interaction framework that combines voice and deictic posture information create more natural HRI system. The visual cues first processed by object detection model gain...

Recognizing human behavior is essential for early interventions in cognitive rehabilitation, particularly older adults. Traditional methods often focus on improving third-person vision but overlook the importance of visual attention during object interactions. This study introduces an egocentric analysis (EBA) framework that uses transfer learning to analyze relationships. Egocentric used extract features from hand movements, detection, and attention. These are then validate hand-object...

This paper introduces an artificial intelligence (AI) interactive system featuring a self-growing memory network designed to enhance self-efficacy, reduce loneliness, and maintain social interaction among the elderly. The dynamically analyzes processes user-written diaries, generating empathic personalized responses tailored each individual. architecture includes experience extraction model, that provides contextual understanding of user’s daily life, chat agent, feedback loop adaptively...