Robot Soccer using Optical Analog VLSI Sensors

Becanovic, Vlatko; Hosseiny, Ramin; Indiveri, Giacomo

doi:10.2316/journal.206.2004.4.206-2718

Cited by 4 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dalam konteks penggunaan sensor untuk mendukung kinerja visual robot, Bečanović dkk. dalam [7] memperkenalkan sensor optik neuromorphic yang disusun oleh rangkaian terpadu tipe VLSI (very large scale integration) dengan kemampuan komputasi gerak dan estimasi posisi spasial objek yang bergerak. Sementara itu, Dodds dkk.…”

Section: Pendahuluanunclassified

Desain dan Realisasi Pemrosesan Citra dengan CMUcam4 untuk Meningkatkan Kinerja Visual Robosoccer

Najmurrokhman¹,

Kusnandar²,

Wibowo³

et al. 2018

Preprint

View full text Add to dashboard Cite

Makalah ini telah dipresentasikan dalam Modern Electrical Engineering Technology and Its Application Seminar (MEETAS) 2016, Kampus Universitas Kristen Maranatha, 28 Oktober 2016. Robot sepakbola (robosoccer) adalah sebuah robothumanoid yang dirancang agar dapat bermain sepak bola seperti layaknya tim sepakbola manusia. Kemampuan yang dimiliki oleh sebuah robosoccer adalah identifikasi terhadap bola, pemain dalam satu tim, pemain lawan, dan gawang. Makalah ini memaparkan tentang desain dan realisasi pemrosesan citra bola, garis, dan gawang untuk meningkatkan kemampuan visual sebuah robot sepakbola (robosoccer). Metode penelitiannyamencakup pelacakan warna dengan menggunakan sensor kamera CMUcam4 yang sudah dilengkapi dengan pemroses citra digitalnya. Pelacakan warna adalah kemampuan untuk mengambil suatu gambar, mengisolasi warna tertentu, dan mengekstrak informasi tentang lokasi suatu daerah gambar yang berisi warna tertentu. Untuk menentukan warna tersebut, diperlukan nilai minimum dan nilai maksimum untuk tiga kanal warna. Setiap warna yang unik dihasilkan melalui prosespencampuran nilai merah, hijau dan biru (RGB) dengankomposisi tertentu. Hasil pengujian menunjukkan bahwapenerapan pengolah citra CMUcam4 dalam aplilasi robosoccer dapat meningkatkan kinerja visual robosoccer dalam mengenali bentuk dan warna bola, gawang, dan tepi garis lapangan.

show abstract

Section: Pendahuluanunclassified

Desain dan Realisasi Pemrosesan Citra dengan CMUcam4 untuk Meningkatkan Kinerja Visual Robosoccer

Najmurrokhman¹,

Kusnandar²,

Wibowo³

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Also relative field of view of sensors and background properties such as static objects, their textures and shades due to ambient light are calculated. In this work the robot is static and the only moving object in the scene is a soccer football whose position is determined by experimental data obtained in previous work [5]. By using the position data together with the collected sensory data, we can recreate the sensory input data in the simulator and use the recorded sensory data as a validation signal.…”

Section: Simulation Environmentmentioning

confidence: 98%

“…(4) All facilitation signals are decayed. (5) The facilitation signal in (2) for the pixel with the largest signal (WTA) is given as output.…”

Section: B Kramers' 1d Motion Sensormentioning

confidence: 99%

“…Early work included solving visual servoing problems for the control of a panning camera system [3] and also hybrid control experiments, where a fast sensor-actuator feedback module was designed [4]. In the domain of machine vision and sensor-fusion, experiments have been performed with the aim to design an object tracker system [5]. In this latest work, several types of neuromorphic vision sensors were used together with reference information from ground truth data.…”

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Modeling of Neuromorphic Vision Sensors in ODE

Becanovic

Günther²,

Bredenfeld³

Proceedings of the 2005 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Three different neuromorphic vision sensors; a 2D smooth optical flow sensor, a 1D tracker sensor and a 1D motion sensor are modeled in a simulator. The sensors are modeled according to their spatio-temporal properties and the model is validated with experimental data obtained in previous work. The model parameters are fitted according to validation data, where a cost function is optimized with a gradient descent approach. The simulator used is the Open Dynamics Engine (ODE) and the experimental data from previous work was collected in a typical RoboCup scenario. A soccer playing robot is here used to provide reference information from a standard digital tracker system. By modeling the output from neuromorphic vision sensors, it is possible to reconstruct the experiment in the simulator. We will present simulated data from this particular experiment and compare it to the ground truth validation data. This work is important in order to reduce the time needed for real-world experiments for the set-up and optimization phase during the integration of such sensors into robotic systems. At the end we will also make an indication of the direction of future research.

show abstract