The goal of this project is to create an autonomous shuttle for the urban Indian last mile. The shuttle will operate on predefined routes and provide hassle free anytime connectivity to modes of public transport like the Metro. To keep the costs per shuttle low, we plan to leverage state-of-the-art Artificial Intelligence and other computational techniques that enable reducing the costs of sensing hardware needed per shuttle. In its first avatar the shuttle will provide connectivity between points in a university campus.
With this in mind, over the next year, we plan to achieve autonomous static obstacle avoidance, lane following, reading of basic traffic signals, and following speed limits. For doing this, during the learning phase, the shuttle builds a 3-D map of the route it will take, and then uses it for navigation. Our current choice of vehicle platform is an electric rickshaw, and currently we are working on providing shuttle service within the IIIT-Delhi campus. We also hope to replicate the above on Mahindra’s latest electric car, the e2o, which we as one of the competitors in the Mahindra Rise Driverless Car Challenge expect to get soon from Mahindra.

The aim of this project is to build using UAVs (Unmanned Aerial Vehicle) with manual remote controls, an intelligent UAV platform with capabilities such as autonomous flying, navigation, and landing, as well as capabilities to perform complex tasks such as automatic air drop, detecting and localizing targets of interest, reaching a specified position or target, etc. UAVs with these capabilities can serve a plethora of applications.

For an intelligent system, design and placement of payload is one of the first and foremost aspects. The project uses off the shelf airframes, assemble it with necessary components to make a basic working UAV. This is then integrated with an autopilot system which adds sensing capabilities and autonomous navigation capability in addition to manual control. In addition to sensors like GPS, compass etc. this platform will also comprise of vision as a passive sensor with a final aim of achieving more complex above mentioned tasks such as detecting objects, autonomous air drop, localizing targets of interest. The ground station system will do status monitoring and receive video feed in real time. The design overall includes a robust power system, autopilot system, data exchange system (to transmit and receive data to and from the ground station). This project is being done by a team of BTech, MTech and Ph.D. students with background in Computer Science and Electronics, and experience is in a variety of fields such as: Aeromodeling, Autonomous Systems, Robotics, Computer Vision, Embedded Systems etc. The team is being provided guidance by faculty.

The team is planning to showcase it's work and design at the prestigious SUAS 2016, the largest unmanned systems competition in the world organized annually by AUVSI Foundation, for which they have already been invited.