- Collaborators 0
- Followers 1
Unmanned Self-Balancing Bicycle with PID Controller
Flying, walking, and roving machines. Browse the expertise on display in these robotics projects.
As the name suggests, we will be using a Deep Bidirectional Recurrent Neural Network with LSTMs (DBRNN) to achieve the state-of-the-art performance described by Graves et al. using a normal speech dataset (no speech impediment). This model will include Mel Frequency Cepstral Coefficients (MFCC) for filtering and feature extraction. We will also use Connectionist Temporal Classification (CTC) for data aligning and labeling unsegmented sequences; CTC is used as the cost function.A Word to ARPAbet phonemes dictionary from CMU is used here as well.
Output phonemes are then post processed by altering the phonemes sequence to generate potential words. Those word are then fed to another Recurrent neural network that acts as a language model assigning probabilities for words to occur given previous word(s). Beam search is to be used for efficient scanning of possible sentences.
This project is likely to have a speaker dependent version to increase the accuracy of Automatic Speech Recognition. TensorFlow is the framework to be used in this project. A GUI will be designed using QT designer for easy use and demonstrations.
Generating the learning data set using Intel's performance libs, training algorithms requires data to be fed to the tool/framework which in return is to be used to train and verify/cross verify the resulting models. Parallelization and vectorized math built into the MKL constitute the beating core of the this phase.
intergraded android SDK graphic design
Testing on both GTAV simulator and on a RacerCar with a TX1
It's an AI bot that controls your music and other music apps, it is in Development mode. Contributors will come to help us.
The Whole Package Complete Solution Natural Language Understanding Tools to design unique conversation scenarios, design corresponding actions and analyze interactions with users.
Cheat-Sheet Document with Pre-Defined Knowledge Included Knowledge Included Leverage predefined knowledge packages collected over several years, including encyclopedic data, weather, news, booking, flight schedules, and much more.
Light Bulb Image Machine Learning The platform learns from examples provided by developers and conversations it has with end users to continuously improve the user experience.
Two Way Conversation with Support Conversation Support Switch seamlessly between conversation topics, while remembering where you left off for each one.
Rotating Cog Integrations Leverage integrations with Alexa, Cortana and messaging platforms (Facebook, Slack, Skype, Cisco Spark, Twilio SMS, etc.).
Space Ship Lifting Off Easy to Get Started Create and deploy a conversational agent in a few days. Continue to train your agent while it learns from conversations it has with end users.
Globe Image Multi-lingual Support Support for 14 languages. More coming soon!
Speed Monitor High Performance We process millions of user requests daily with 99.99% guaranteed uptime.
This project is focused on designing a mechanical structure of an unmanned bicycle and a controller by using a classic control, PD control and applies it to AU Self-balancing Bicycle (AUSB). The main objective of this project is to control the balancing ability of the bicycle automatically. The main concept applying in this project is the Gyroscopic effect. Data obtained from the Gyroscope sensor will be the process variable (θpv) of the controlling system, which will be captured in a dsPIC microcontroller. This microcontroller will control the output in term of percentage of Pulse-Width-Modulation (PWM) with the value appropriate due to the error obtained from the Gyroscope sensor and send this output to control the direction of the flywheel.
Cisco networking With artificial intelligence
The obstacle avoiding robot uses the ultrasonic sensor to avoid obstacles and find the most suitable path to follow. The sensor checks for obstacles in three different directions : 1.Forward 2.Left (45 degrees angle) 3.Right (45 degrees angle) Depending on the data obtained from the three directions ,a more suitable path is determined in which the bot follows (i.e the path with least amount of obstacles) The Intel Galileo board is used in the project.
The path finder is a pair of smart glasses for the blind that helps them manouvre around and find the best suitable path of movement. It works on the principle of obstacle avoidance using different sensors. The sensors check for obstacles in four key areas : 1.Forward (Direct line of sight) 2.Left (45 degrees angle) 3.Right (45 degrees angle) 4.Ground (45 degrees angle) Vibration modules are used as the mode of communication to the blind in order to guide him/her around.
The real time data such as the specific GPRS coordinates is also transmitted to the cloud for constant monitoring by an auxiliary person.
Unmanned Self-Balancing Bicycle with PID Controller
Creating a conversational user experience with natural language interactions.
Current end to end networks work mostly on ConvNets, my approach is to use LSTMs to improve accur...
Ranchi, Jharkhand, India
Sector - 106, Noida, Uttar Pradesh 201304, India
Indian born, Detroit raised
Detroit, MI, USA
Shalimar Bagh, New Delhi, Delhi 110088, India
A two-wheeled robot controlled on BLE
EGG - It is a product that looks to combine the best technologies out there as an educational too...
Minnowboard Intelligent Expansion (hardware components)
Its an iot system which will automate the entire process of agriculture and gardenning. we just ...
Triton UAS is an engineering student organization at UC San Diego that develops deep learning sys...
b08 the Robot is in pre-seed stage and we are recruiting developers of all skills sets and of all...
A platform that integrates with multiple individual robots or devices to leverage machine learnin...
An opensource telepresence omnidirection bartending robot built using the IoT platform Octoblu an...
Wi-Fi Connected robotic ball with HD camera, microphone, speaker & array of environmental monitor...
Designed for your backyard, two mini drones play a game of strategy mixed with piloting skill.
prototype to manage and subdivide bottle cups by shape and color.
Small rover based on Windows 10 IoT Core that can explore an environment or can be remote control...
ViVACITY is a life monitoring system that runs hidden behind a robot.