Animal-in-the-loop system to investigate adaptive behavior
S. Shigaki a, M. R. Fikria, C. Hernandez Reyesa, T. Sakuraib∗, N. Ando b, D. Kurabayashi a, R. Kanzakib and H. Sezutsuc
aTokyo Institute of Technology, Meguro-ku, Tokyo, Japan; bThe University of Tokyo, Meguro-ku, Tokyo, Japan; cNational Agriculture and Food Research Organization, Tsukuba, Ibaraki, Japan
ABSTR AC T
In this research, we aim to model an adaptive behavior of an animal and implement it to an autonomous robot. The conventional bio-inspired algorithm is difficult to demonstrate the ability as much as the animal because it models without considering dynamic characteristics of the robot. Therefore, in this study, we constructed an animal-in-the-loop system, which is a novel experimental system for identifying the adaptive behavior of the animal in a form that considers the dynamic characteristics of the robot to be implemented.
KEY WORDS
Animal-in-the-loop system; odor source search; silkworm moth; micro quadrotor
Balancing control of a bicycle-riding humanoid robot with center of gravity
estimation
Chun-Feng Huanga, Yen-Chun Tungb, Hao-Tien Lub and T.-J. Yehb
aAdvanced Robotics Co. Ltd., Taipei, Taiwan; bDepartment of Power Mechanical Engineering, National Tsing Hua University, Hsinchu, Taiwan
ABSTR AC T
In this research, a miniaturized humanoid robot is constructed to ride and pedal a bicycle of comparable size. The design of the controller for the robot to balance and steer the bicycle using the handlebar is of particular interest. The controller possesses the capability to estimate the uncertain center of gravity of the robot-bicycle system and then incorporate such an estimation to enhance control performance. A general control framework which can achieve asymptotic stability under uncertain measurement biases is adopted for controller design. Using the framework, the stability of the control system is analytically guaranteed and its control parameters can be determined in a systematic manner. Both simulations and experiments verify that the proposed controller can automatically counteract the mass imbalance in the robot-bicycle system and allow it to perform straight-line steering without using camera visual feedback.
KEY WORDS
Bicycle dynamics; humanoid robots; uncertain system control; inverted-pendulum systems
Integrating SLAM and gas distribution mapping (SLAM-GDM) for real-time gas
source localization
Kamarulzaman Kamarudina,b, Ali Yeon Md Shakaffa,b, Victor Hernandez Bennettsc, Syed Muhammad Mamduha, Ammar Zakaria a,b, Retnam Visvanathana, Ahmad Shakaff Ali Yeona and Latifah Munirah Kamarudin a
aCentre of Excellence for Advanced Sensor Technology (CEASTech), Universiti Malaysia Perlis, Arau, Malaysia; bSchool of Mechatronics Engineering, Universiti Malaysia Perlis (UniMAP), Arau, Malaysia; cApplied Autonomous Sensor Systems, Örebro University, Örebro, Sweden
ABSTR AC T
Gas distribution mapping (GDM) learns models of the spatial distribution of gas concentrations across 2D/3D environments, among others, for the purpose of localizing gas sources. GDM requires run-time robot positioning in order to associate measurements with locations in a global coordinate frame. Most approaches assume that the robot has perfect knowledge about its position, which does not necessarily hold in realistic scenarios. We argue that the simultaneous localization and mapping (SLAM) algorithm should be used together with GDM to allow operation in an unknown environment. This paper proposes an SLAM-GDM approach that combines Hector SLAM and Kernel DM + V through a map merging technique. We argue that Hector SLAM is suitable for the SLAM-GDM approach since it does not perform loop closure or global corrections, which in turn would require to re-compute the gas distribution map. Real-time experiments were conducted in an environment with single and multiple gas sources. The results showed that the predictions of gas source location in all trials were often correct to around 0.5–1.5 m for the large indoor area being tested. The results also verified that the proposed SLAM-GDM approach and the designed system were able to achieve real-time operation.
KEY WORDS
Gas source localization; gas distribution mapping; SLAM; mobile robot; gas sensing; metal oxide gas sensor
Simultaneous pose and reliability estimation using convolutional neural network
and Rao–Blackwellized particle filter
Naoki Akaia, Luis Yoichi Moralesa and Hiroshi Muraseb
aInstitute of Innovation for Future Society, Nagoya University, Nagoya, Japan; bGraduate School of Information Science, Nagoya University, Nagoya, Japan
ABSTR AC T
In this study, we propose a novel localization approach that simultaneously estimates the reliability of estimation results. In the approach, a convolutional neural network (CNN) is used to make decision whether the localization process has failed or not. We train the CNN using a dataset that includes successful localization results and faults. However, the decision will contain some noise and many misdetection results may occur when the decision made by the CNN is used directly to detect faults. Therefore, we estimate both a robot’s pose and reliability of the localization results based on the decision. To simultaneously estimate the robot’s pose and reliability, we propose a new graphical model and implement a Rao–Blackwellized particle filter based on the model. We evaluated the proposed approach based on simulations and actual environments, which showed that the reliability estimated by the proposed approach can be used as an exact criterion for detecting localization faults. In addition, we show that the proposed approach can be applied in actual environments even when a dataset created from a simulation is used to train the KEY WORDS
Localization; failure detection; reliability; convolutional neural network; Rao–Blackwellized particle filter
