Exploring the Performance of a Sensor-Fusion-based Navigation System for Human Following Companion Robots

Tsun, Mark Tee Kit; Jo, Hudyjaya Siswoyo

doi:10.18178/ijmerr.7.6.590-598

Cited by 8 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A solution with cameras in addition to laser range sensors was presented by Shimizu et al [314], who achieve markerless results in indoor settings. In contrast, Kit Tsun et al [311] use a depth camera, an active marker and proximity sensors as well as simulated environments. Two approaches using reinforcement learning have been proposed by Wang et al [315] and Bayoumi et al [316], with the former learning the correct social distance when interacting with the human and the latter learning about the human's goal so the robot can navigate efficiently even when the human makes detours.…”

Section: Discussionmentioning

confidence: 99%

A Survey on Human-aware Robot Navigation

Möller¹,

Furnari²,

Battiato³

et al. 2021

Preprint

View full text Add to dashboard Cite

Intelligent systems are increasingly part of our everyday lives and have been integrated seamlessly to the point where it is difficult to imagine a world without them. Physical manifestations of those systems on the other hand, in the form of embodied agents or robots, have so far been used only for specific applications and are often limited to functional roles (e.g. in the industry, entertainment and military fields). Given the current growth and innovation in the research communities concerned with the topics of robot navigation, human-robot-interaction and human activity recognition, it seems like this might soon change. Robots are increasingly easy to obtain and use and the acceptance of them in general is growing. However, the design of a socially compliant robot that can function as a companion needs to take various areas of research into account. This paper is concerned with the navigation aspect of a socially-compliant robot and provides a survey of existing solutions for the relevant areas of research as well as an outlook on possible future directions.

show abstract

Section: Discussionmentioning

confidence: 99%

A Survey on Human-aware Robot Navigation

Möller¹,

Furnari²,

Battiato³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Previous research on autonomous navigation has proposed the integration of different sensor modalities, including an Inertial Measurement Unit (IMU) and GPS [11,12], IMU and wheel encoders [13,14], and LiDAR-only applications [15,16]. Combination of an IMU and camera within an Extended Kalman Filter to estimate the Euler angles with good accuracy was discussed in [17,18]. While all of these navigation approaches can correctly operate in indoor environments, almost none of them have been extensively tested in outdoor applications due to the non-structured nature of the environment.…”

Section: Introductionmentioning

confidence: 99%

RoboNav: An Affordable Yet Highly Accurate Navigation System for Autonomous Agricultural Robots

2022

View full text Add to dashboard Cite

The paper presents RoboNav, a cost-effective and accurate decimeter-grade navigation system that can be used for deployment in the field of autonomous agricultural robots. The novelty of the system is the reliance on a dual GPS configuration based on two u-blox modules that work in conjunction with three low-cost inertial sensors within a Gaussian Sum Filter able to combine multiple Extended Kalman filters dealing with IMU bias and GPS signal loss. The system provides estimation of both position and heading with high precision and robustness, at a significantly lower cost than existing equivalent navigation systems. RoboNav is validated in a commercial vineyard by performing experimental tests using an all-terrain tracked robot commanded to follow a series of GPS waypoints, trying to minimize the crosstrack error and showing average errors on the order of 0.2 m and 0.2∘ for the measurement of position and yaw angle, respectively.

show abstract

“…They were able to achieve very good performance; however, the camera in the setup was fixed. Tsun et al 25 considered the trajectory planning problem of a person-following robot. They proposed a very nice fusion algorithm but only presented simulation results.…”

Section: Introductionmentioning

confidence: 99%

Dynamic human object recognition by combining color and depth information with a clothing image histogram

Wang

Yen

et al. 2019

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Human object detection, tracking, and recognition have applications in many areas, such as in the development of assistance robots and intelligent monitoring systems. The emergence of an RGB-D camera, namely the Kinect v2, has simplified the process of human object detection and tracking. Color space methods are dependent on lighting conditions. Because skeleton-tracking algorithms are based on depth images, they are light invariant relative to color space methods. However, skeleton information may sometimes be incorrect or become lost. An algorithm for human-target recognition is thus required. Therefore, this study proposes a human-target tracking and recognition system combining RGB images, depth images, body index, and skeleton information. The system first extracts the color information of five body parts (two upper arms, the torso, and two thighs) using color, depth, and skeleton information. The system then analyzes the color information using a mixed nine-dimensional histogram and single-color analysis method. The algorithm also includes overlap detection during the process of human-target tracking to prevent misidentification caused by occlusion. To test the proposed system, various scenarios were carefully designed to simulate the extremely complex environmental changes characteristic of the real world. Furthermore, the dynamic statistical method of event statistics was used to collect results. Experiments revealed that the proposed method is robust under varying lighting conditions and increases the success rate for individuals wearing similar clothing with monochrome colors.

show abstract

Exploring the Performance of a Sensor-Fusion-based Navigation System for Human Following Companion Robots

Cited by 8 publications

References 14 publications

A Survey on Human-aware Robot Navigation

A Survey on Human-aware Robot Navigation

RoboNav: An Affordable Yet Highly Accurate Navigation System for Autonomous Agricultural Robots

Dynamic human object recognition by combining color and depth information with a clothing image histogram

Contact Info

Product

Resources

About