Follow me robot using bluetooth-based position estimation

Pradeep, B; Rahul, E. S.; Bhavani, Rao R.

doi:10.1109/icacci.2017.8125903

Cited by 12 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our implementation approach is in contrast to traditional approaches for implementing such a robotic controller, which rely on hand-designed rules applied to infrared sensors [57] camera inputs [58], [59], or local localization protocols [60]. Perhaps the closest work to ours is the setup described in [61], which uses a stereo camera setup and machine learning using Support Vector Machines (SVMs).…”

Section: Experimental Evaluation: a Case-studymentioning

confidence: 99%

Adversarial Training is Not Ready for Robot Learning

Lechner¹,

Hasani²,

Grosu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Adversarial training is an effective method to train deep learning models that are resilient to norm-bounded perturbations, with the cost of nominal performance drop. While adversarial training appears to enhance the robustness and safety of a deep model deployed in open-world decisioncritical applications, counterintuitively, it induces undesired behaviors in robot learning settings. In this paper, we show theoretically and experimentally that neural controllers obtained via adversarial training are subjected to three types of defects, namely transient, systematic, and conditional errors. We first generalize adversarial training to a safety-domain optimization scheme allowing for more generic specifications. We then prove that such a learning process tends to cause certain error profiles. We support our theoretical results by a thorough experimental safety analysis in a robot-learning task. Our results suggest that adversarial training is not yet ready for robot learning.

show abstract

Section: Experimental Evaluation: a Case-studymentioning

confidence: 99%

Adversarial Training is Not Ready for Robot Learning

Lechner¹,

Hasani²,

Grosu³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The ability of tracking and following users is projected as a main task for personal service robots and the design of human robot interaction in for these robotic systems has been evaluated (e.g. [14][15]. In general, tracking is defined as following or detecting of a target, e.g.…”

Section: Autonomous Mobilitymentioning

confidence: 99%

Requirement Analysis for Personal Autonomous Driving Robotic Systems in Urban Mobility

Bärnklau

Rötting

Roesler

et al. 2021

HCI in Mobility, Transport, and Automotive Systems

View full text Add to dashboard Cite

Urban mobility is changing due to the emergence of new technologies like autonomously navigating robots. In the future, various transport operators and micro mobility services will be integrated in an increasingly complex mobility system, potentially realizing benefits such as a reduction of congestion, travel costs, and emissions.The field of personal robotic transport agents is projected to increasingly play a role in urban mobility, hence in this study, prospective target groups and corresponding user needs concerning human-following robots for smart urban mobility applications are investigated. Building on an extensive literature review, three focus groups with a total of 19 participants are conducted, utilizing scenario-based design and personas. Results show clearly definable user needs and potential technological requirements for mobile robots deployed in urban road environments. The two most mentioned potential applications were found in the fields of leisure applications and in healthcare for elderly people.Based on these focus group results, two personal automated driving robots which differ in function, operation and interaction were designed. The focus group-based results and derived requirements shed light on the importance of context-sensitivity of robot design.

show abstract

“…In order for the robot to recognize a human, it requires a mechanism that provides it information so that it can function accordingly. There are various methods in the literature that deals with issue on human detection for example the utilization laser scanner [7], real-time human face tracking [8], Kinect sensor [9], fusion of Bluetooth and Inertial Measurement Unit (IMU) [10] and RGB-D sensor [11]. These methods produced encouraging results in human detection, but majority of them require complex computational algorithm and high-end sensors that can possibly increase the cost of development.…”

Section: Introductionmentioning

confidence: 99%

CREC: Camera-Based Mobile Robot for Elderly Care

Jamatolail¹

2019

IJATCSE

View full text Add to dashboard Cite

Technologies that permits remote monitoring can be very helpful in reducing concerns of long-distance caregiving especially for elderly care. This work describes the design and development of a Camera-based mobile Robot for Elderly Care (CREC). A Pixy CMUcam5 camera is used as the main intermediary between the elderly and the movement of the robot. This camera uses a marker or tag to follow and monitor the elderly. Furthermore, a range finder sensor, Ultrasonic Sensor HC-SR04 is used as the main sensor to avoid obstacles as it is easy to inter-face and low-cost. An Arduino microprocessor is utilized to control the tyres of the mobile robot, so that the robot can follow the elderly with precision. In the current work, the robot is specifically designed to be used indoors. Several experiment have been carried out to show the usefulness of CREC. Experimental results demonstrated that CREC is capable to avoid obstacle and follow the marker tagged static and moving target successfully.

show abstract

Follow me robot using bluetooth-based position estimation

Cited by 12 publications

References 7 publications

Adversarial Training is Not Ready for Robot Learning

Adversarial Training is Not Ready for Robot Learning

Requirement Analysis for Personal Autonomous Driving Robotic Systems in Urban Mobility

CREC: Camera-Based Mobile Robot for Elderly Care

Contact Info

Product

Resources

About