Building the Next Big Automated Driving Technology!
You just landed on BITS Pilani's Autonomous Vehicle Research Team's page!
Who are we?
A team of undergraduate student researchers at The Centre for Robotics & Intelligent Systems (CRIS), BITS Pilani. Spearheaded by Prof. Bijay Kumar Rout, we aim to develop a fully autonomous vehicle for Indian Roads.
- Team members have worked in the development of autonomous cars in foreign research facilities (USA & Germany).
- The team has previously been involved in building a prototype, Autonomous Ground Vehicles (AGVs), with autonomous capabilities.
- One of these prototypes was demonstrated at DRDO Robotics & Unmanned Systems Exposition-2018. It was highly praised by the scientists on the committee and won the first position with a cash prize of Rs. 60,000. It also made us one of the country's top 6 teams for the final exposition.
The name “Sally Robotics”
As with several other key technologies, Isaac Asimov also predicted autonomous cars way back in 1953. He published a short story, Sally, about an autonomous car of the same name who ends up saving the protagonist's life. The name of our team is an homage to Asimov, who envisioned the first self-driving car.
As robotics researchers we wish to take the challenge head on and aim to develop an AI model based on the spatial cognitive abilities of the Indian driver, which can indeed make vehicles demonstrate autonomous capabilities on highly unstructured Indian roads.
What do we do?
Our work entails several subsystems, such as Computer Vision,
Deep Learning, Localization, Path Planning, Control Systems, Sensor Fusion,
Middleware etc. with varying levels of complexity in each of them.
This subsystem seeks to automate the tasks that a human visual system can do. Essentially, it is meant to perform the work which is analogous to the human eye, for the vehicle. Computer Vision at Sally Robotics is primarily working on the implementation of: Object Detection, Lane Line Detection & Segmentation tasks.
- Work it entails:
- Image Classification
- Object Localization
- Object Detection
- Semantic Segmentation
- Instance Segmentation
- Image captioning
This subsystem works to automate the process of determining the position of the vehicle and comprehension of the environment around it. This involves the creation of maps (by the vehicle) and estimation of its own position on the said map.
- For this we use a three-fold approach :
1. Vehicle Pose Estimation : Estimation of the vehicle's position and orientation.
2. Sensor Fusion : Interpretation and compilation of data from various sensors
3. Simultaneous Localization and Mapping (SLAM) algorithms : Determination of pose with respect to dynamic maps of the environment.
This subsystem aims to automate the decision making for the vehicle, viz. planning an efficient trajectory and controlling itself in the environment (as understood using sensory inputs).
- The work entails :
1. Behaviour Planning
2. Motion Planning
3. Obstacle avoidance
4. Vehicle Dynamics
Aims at designing and implementing solutions into the car for car actuation and sensor mounting to aid and implement Driverless systems.
- Work it entails:
1. Actuation of car controls
2. Vibrational analysis of points on car chassis
3. Sensor mounting
Made with ♥ at BITS Pilani