A swarm of intelligent thruster based robots that can maneuver around and work collaboratively in group to complete a set of goals. Powered by Deep Learning and Reinforcement Learning, the robot swarms can navigate autonomously and react to situations intelligently. website - arcred.space
With the rapid increase of urban population and surveillance cameras, crowd scene analysis is of great importance. We are developing an application system to perform crowd counting and crowd scene analysis on the edge computing device.
This fully autonomous bot's task was to start from (0,0) position of the grid and reach the destination coordinates while avoiding the obstacle in the course. The second part is to retrace the route in the shortest path.
A line following autonomous robot capable of following wall as well. It can switch between line following or wall following and can do both in parallel.
In this project, we propose an end-to-end multi-task regression-based learning approach capable of defining flight commands for navigation and exploration under the forest canopy, regardless of the presence of trails or additional sensors (i.e., GPS).
A tennis ball retriever using #Intel 's D415 RealSense camera and #OpenVINO for object detection. Great project to use computer vision, object detection, and robotics!
The hotdog app of Intelligent Robotics.
A Solution for ALL that revolutionizes the driving ecosystem . We aim at overcoming the pitfalls of the human errors prevalent among drivers all over the world .The concept behind the Buzz Kill is to actively monitor the driver’s attention levels and Eye Aspect Ratio .
A custom designed and custom engineered LED mask using addressable LEDs. This was one of the most complex system that i've got to develop. 3600 Leds divided in 16 Array's each one is feed data using parallel outputs from a SAM3X micro and the graphics is generated using a UPBoard.
It's a portable device that can identify what skin diseases that we are suffering from with the help of a camera on it. we can simply do this concept on mobile devices but once we've tried the same we haven't satisfied with the accuracy because the input is even biased with the lights, shades of the environment that we are taking pictures from. so this might be a closed camera with a proper single channel light on it. so we can easily collect the dataset from the same device and then we can ...
A smart and innovative method to analyse a driver's behaviour on the road based on real data acquired from the vehicle and camera input based on Facial feature mapping and OBD data models.
Designed and developed the ping pong game based on Game Trees in ROS & Gazebo. This system can be used as an assignment in Game Trees for the course of Artificial Intelligence.
Humans acquire complex skills by exploiting previously learned skills and making transitions between them. To empower machines with this ability, we propose a method that can learn transition policies which effectively connect primitive skills to perform sequential tasks without handcrafted rewards. To efficiently train our transition policies, we introduce proximity predictors which induce rewards gauging proximity to suitable initial states for the next skill. The proposed method is evaluat...