Payam Nazemzadeh

Indoor Positioning of a Robotic Walking Assistant for Large Public Environments

Indoor localization and position tracking are essential to support applications and services for ambient-assisted living. While the problem of indoor localization is still open and already quite complex per se, in large public places, additional issues of cost, accuracy, and scalability arise. In this paper, the position estimation and tracking technique developed within the project devices for assisted living (DALi) is described, analyzed through simulations, and finally validated by means of a variety of experiments on the field. The goal of the DALi project is to design a robotic wheeled walker guiding people with psychomotor problems. Indeed, people with motor or cognitive impairments are often afraid of moving in large and crowded environments (e.g., because they could lose the sense of direction). In order to mitigate this problem, the position tracking approach described in this paper is based on multisensor data fusion and it is conceived to assure a good tradeoff between target accuracy, level of confidence, and deployment costs. Quite interestingly, the same approach could be used for indoor automated guided vehicles and robotics.

An indoor position tracking technique based on data fusion for ambient assisted living

Accurate indoor position tracking of moving users is essential in ambient assisted living (AAL) applications. In this paper, in view of designing a smart rollator helping impaired or elderly people to navigate in indoor environments (e.g. shopping malls, railway stations or airports), a position tracking estimation technique is described and the performance of different variants are compared through simulations. The proposed solution is based on an extended Kalman filter (EKF), which in turn relies on the measurement data provided by two encoders, a gyroscope a short-range radio-frequency identification (RFID) system and a possible further low-rate, high-accuracy orientation measurement system. Some simulation results confirm that the position tracking accuracy of the proposed technique is fairly good even if the distance between RFID tags is quite large (i.e. in the order of a few meters).

Design and performance analysis of an indoor position tracking technique for smart rollators

This paper presents a position tracking technique based on multisensor data fusion for rollators helping elderly people to move safely in large indoor spaces such as public buildings, shopping malls or airports. The proposed technique has been developed within the FP7 project DALi, and relies on an extended Kalman filter processing data from dead-reckoning sensors (i.e. encoders and gyroscopes), a short-range radio frequency identification (RFID) system and a front Kinect camera. As known, position tracking based on dead-reckoning sensors only is intrinsically affected by growing uncertainty. In order to keep such uncertainty within wanted boundaries, the position values are occasionally updated using a coarse-grained grid of low-cost passive RFID tags with known coordinates in a given map-based reference frame. Unfortunately, RFID tag detection does not provide any information about the orientation of the rollator. Therefore, a front camera detecting some markers on the walls is used to adjust direction. Of course, the data rate from both the RFID reader and the camera is not constant, as it depends on the actual users trajectory and on the distance between pairs of RFID tags and pairs of markers. Therefore, the average distance between tags and markers should be properly set to achieve a good trade-off between overall deployment costs and accuracy. In the paper, the results of a simulation-based performance analysis are reported in view of implementing the proposed localization and tracking technique in a real environment.

Indoor positioning of wheeled devices for Ambient Assisted Living: A case study

Indoor navigation is a well-known research topic whose relevance has been steadily growing in the last years thrust by considerable commercial interests as well as by the need for supporting and guiding users in large public environments, such as stations, airports or shopping malls. People with motion or cognitive impairments could perceive large crowded environments as intimidating. In such situations, a smart wheeled walker able to estimate its own position autonomously could be used to guide users safely towards a wanted destination. Two strong requirements for this kind of applications are: low deployment costs and the capability to work in large and crowded environments. The position tracking technique presented in this paper is based on an Extended Kalman Filter (EKF) and is analyzed through simulations in view of minimizing the amount of sensors and devices in the environment.

Optimal placement of landmarks for indoor localization using sensors with a limited range

Indoor positioning often requires detecting and recognizing ad-hoc landmarks or anchor points with known coordinates and/or a given orientation within a given reference frame. Typically, the available kind of sensors and their detection area determine the landmark features and position. Of course, an excessive use of landmarks pose serious scalability and cost issues, whereas, on the other hand, a too-low amount of deployed landmarks may create areas where agents position is hard to track or localization accuracy drops. In addition, often sensors are not omni-directional. In this paper, the optimal placement problem of landmarks detected by sensors with a limited detection area is addressed in the general case of wide-open, ideally unbounded, rooms. First, landmarks placement optimization is performed numerically. Then, a closed-form expression of the optimal distance between landmarks on a regular pattern is determined as a function of both the reading range and the directional properties of the sensor considered. Finally, the performances of the chosen placement strategy in more realistic indoor environments (i.e. consisting of multiple rooms with obstacles therein) are evaluated through simulations assuming, without loss of generality, that a wheeled robot equipped with a front camera adjusts its own position by detecting suitable visual landmarks.

Optimal placement of passive sensors for robot localisation

We consider the problem of self-localisation for a mobile robot in an environment with a requested level of accuracy. The robot moves in a known environment following typical trajectories, which can be characterised in statistical terms. One of the main drivers of this paper is its application to assistive robots guiding senior or impaired users in shopping centres or in other public spaces. To localise itself the robot uses onboard sensors such as encoders and inertial platforms. The level of noise in these sensors and the lack of absolute measurements determines a steady growth of the uncertainty on its position. To alleviate the problem, we assume the presence of a number of visual markers deployed in the environment. Whenever the robot comes across one of these sensors, the uncertainty on its position is reset. In the paper, we show a methodology to minimise the number of these sensors and to select their position so that the uncertainty is never worse than a given target threshold with an assigned probability.

A Smart Walking Assistant for Safe Navigation in Complex Indoor Environments

Large and crowded public places can easily disorientate elderly people. The EU FP7 project Devices for Assisted Living (DALi) aims at developing a robotic wheeled walker able to assist people with moderate cognitive problems to navigate in complex indoor environments where other people, obstacles and multiple points of interest may confuse or intimidate the users. The walking assistant, called c-Walker, is designed to monitor the space around the user, to detect possible hazards and to plan the best route towards a given point of interest. In this chapter, an overview of the system and some of its most important functions are described.

Indoor Localization of Mobile Robots Through QR Code Detection and Dead Reckoning Data Fusion

Many techniques for robot localization rely on the assumption that both process and measurement noises are uncorrelated, white, and normally distributed. However, if this assumption does not hold, these techniques are no longer optimal and, in addition, the maximum estimation errors can be hardly kept under control. In this paper, this problem is addressed by means of a tailored extended H

c-Walker: A Cyber-Physical System for Ambient Assisted Living

_\infty

Navigation assistance and guidance of older adults across complex public spaces: the DALi approach

filter (EHF) fusing odometry and gyroscope data with position and heading measurements based on quick response (QR) code landmark recognition. In particular, it is shown that, by properly tuning EHF parameters and by using an adaptive mechanism to avoid finite escape time phenomena, it is possible to achieve a higher localization accuracy than using other dynamic estimators, even if QR codes are detected sporadically. Also, the proposed approach ensures a good tradeoff in terms of computational burden, convergence time, and deployment complexity.