Hudyjaya Siswoyo Jo

A human orientation tracking system using Template Matching and active Infrared marker

Human tracking research has been reinforced with the introduction of vision-based motion tracking sensors such as Microsoft Kinect and Intel RealSense since 2009. No longer limited to just wearable sensors, embedded environments and 2D camera feed, stereoscopic digital cameras and Infrared imaging has enabled perceivable depth and distance to contribute to geo-location, activity tracking, and automated detection of abnormal events. However, current motion tracking systems have a limited zone of detection and tracking, subjected to environmental lighting, lens occlusion and hardware factors. This study proposes and demonstrates the possibility of complementing these existing sensors with a simple human tracking system that can be used to direct their reorientation in order to maintain the tracked person within their optimal zone of detection. The prototype in this study utilizes an Infrared Camera and an active Infrared marker to track the pan orientation of a person by means of Template Matching - finding a template image match that indicates the angle of marker pan. By knowing the targets angle of pan, a Microsoft Kinect sensor can be autonomously relocated to the front of the person via the shortest path around. This implementation may also be retooled for other systems that have a smaller zone of detection.

Modelling and control of a novel hip-mass carrying minimalist bipedal robot with four degrees of freedom

The paper presents a simplified mathematical model of the bipedal walking robot with four degrees of freedom. It presents a novel sensing and balancing method for the bipedal robot with minimum possible for walk degrees of freedom. The proposed method involves the design of semi-rigid ankle to facilitate fast and accurate measurements of the sideway (sagittal) instability of the walking robot. The use of new hip-mass carrying strategy in forward direction and system of two counter masses for the sideway body balancing allows to decouple the forward walking algorithms from the robot stability restoring solutions. The system of two different masses helps to improve response time and efficiency of the balancing system. The developed control algorithms provide continuous stability of the robot while it walks in forward direction by means of only four DC actuators. The smooth legs trajectory planning is implemented to minimise the foot-ground impact and jerky motions at the joints. The efficiency of the proposed control algorithms are tested and verified by using MATLAB Simulink computer tools.

An Improved Indoor Robot Human-Following Navigation Model Using Depth Camera, Active IR Marker and Proximity Sensors Fusion

Creating a navigation system for autonomous companion robots has always been a difficult process, which must contend with a dynamically changing environment, which is populated by a myriad of obstructions and an unspecific number of people, other than the intended person, to follow. This study documents the implementation of an indoor autonomous robot navigation model, based on multi-sensor fusion, using Microsoft Robotics Developer Studio 4 (MRDS). The model relies on a depth camera, a limited array of proximity sensors and an active IR marker tracking system. This allows the robot to lock onto the correct target for human-following, while approximating the best starting direction to begin maneuvering around obstacles for minimum required motion. The system is implemented according to a navigation algorithm that transforms the data from all three types of sensors into tendency arrays and fuses them to determine whether to take a leftward or rightward route around an encountered obstacle. The decision process considers visible short, medium and long-range obstructions and the current position of the target person. The system is implemented using MRDS and its functional test performance is presented over a series of Virtual Simulation Environment scenarios, greenlighting further extensive benchmark simulations.

Dynamic modelling and walk simulation for a new four-degree-of-freedom parallelogram bipedal robot with sideways stability control

Abstract The paper presents a simplified mathematical model of a two-leg walking robot with four degrees of freedom. It presents a novel method of sensing and balancing for the bipedal robot with the minimum possible number of degrees of freedom for the walk. The proposed method involves the design of a semi-rigid ankle to facilitate fast and accurate measurements of the sideways (sagittal) instability of the walking robot. The use of a new hip-mass carrying strategy in the forward direction and a system of two counter-masses for the sideways body balancing enables us to decouple the forward walking algorithms from the robot stability issues. The system of two different masses helps to improve the response time and efficiency of the balancing system. The control algorithms developed provide continuous stability of the robot while it walks in a forward direction by actuating its four DC motors. Smooth leg trajectory planning is implemented to minimize the foot–ground impact and jerky motions at the joints. The efficiency of the proposed control algorithms is tested and verified by using MATLAB Simulink computer tools.

Proposing a Sensor Fusion Technique Utilizing Depth and Ranging Sensors for Combined Human Following and Indoor Robot Navigation

One of the main challenges faced in developing autonomous navigation for indoor robots is designing the strategy to account for a combination of obstacle avoidance while fulfilling additional maneuvering requirements. An existing child-following companion robot prototype called CARMI is used as a case study for this paper. CARMIs main function is to autonomously follow a child, maintaining her within the optimal detection zone of its vision-based activity tracking system, all the while navigating through furniture and obstructions. This paper examines CARMIs requirements and surveys the state-of-the-art of indoor navigation research, culminating in a design and proposal of a sensor-fusion technique combining the depth sensor, ranging sensor array and Active IR marker tracking system. The aim is to realize a robot navigation system for both person-following and obstacle avoidance using this novel method inspired by the Wandering Standpoint Algorithm and Potential Field Method.

Pathfinding Decision-Making Using Proximity Sensors, Depth Camera and Active IR Marker Tracking Data Fusion for Human Following Companion Robot

Assistive companion robots face a multitude of problems presented by a combination of environmental and hardware factors in addition to the nature of their operation. This is most evident in robots developed for following human subjects in indoor locale without the aid of an embedded environment or complex navigational facilities such as Simultaneous Localization and mapping (SLAM). This paper centers on the implementation and initial simulation of a navigation system that is developed for CARMI, a Companion Avatar Robot for the Mitigation of Injuries. This system utilizes the Microsoft Kinects depth camera, an Active IR Marker tracking system and the robots ultrasonic perimeter sensor array for simultaneous human following and obstacle avoidance while centering the Kinect device in the direction of an autistic child. Initial simulation results are presented to show successful functional capabilities of the system at discerning an approach direction based on depth, ranging and marker sensor data fusion. The conclusion of this paper greenlights simulations for more extensive navigational scenarios.

Development of omnidirectional self-balancing robot

The omnidirectional self-balancing robot or otherwise known as ballbot belongs to a special class of balancing robots. With only one contact point with the ground, ballbot is able to achieve a higher degree of agility with a lower footprint than most mobile robots. While practical applications of balancing platforms such as Segway PT have gained much traction over the last decade, directional limitations in movements are still prevalent in wheeled robots. To achieve omnidirectional motion, a ball is used as a replacement to wheels. Similar to the concept of inverted pendulum, self-balancing is achieved using a closed-loop control system. In this paper, we propose the implementation of a minimalist and low cost ball-balancing robot that utilizes off-the-shelf components that are widely available in the market with the aim to create an affordable platform to study and design control strategies for ballbots.

Development of Blimp Platform for Aerial Photography

This paper presents the development of a semi-automated blimp platform for aerial photography. The blimp can be tele-operated from a ground station and is capable of autonomously holding its heading and altitude when the pilot releases control. The blimp consists of a helium-filled envelope to achieve the buoyancy and a pair of propellers to drive the blimp in the desired direction. A basic control algorithm and sensing system are also proposed to control and maintain the heading and altitude of the blimp.

A Window Climbing Robot

This paper presents the design and fabrication of a Window Climbing Robot (WCR), which is a small-scale or miniature robot that is capable of climbing the windows or glass in a vertical motion. While operating in the vertical motion or climbing, the WCR has the capabilities in performing tasks such as cleaning, inspection, surveillance and maintenance. The WCR can perform these duties without the need of actual human intervention. The robot is able to operate autonomously with the aid of sensors. The robot can be placed onto the surfaces such as glass using the pneumatic-system with suction-power provided by eight suction-cups. The double-belting gear driving mechanism moving the robot is shown and explained. The pneumatic-based suction system is illustrated and the fabricated prototype of the robot is also shown in this paper.