I am a graduate student in Robotics, Systems and Controls program at ETH Zurich. My research interests lie in designing learning-based systems for navigation and manipulation in unknown environments. I am currently working at Robotic Systems Lab under Prof. Marco Hutter on learning locomotion-manipulation policies for ANYmal.

I graduated from IIT Kanpur in May 2018 with a Bachelors in Electrical Engineering. In the summer of 2017, I worked with Prof. Wolfram Burgard on predicting landing sites from aerial images. During my undergraduate program, I co-founded the AUV team for marine robotics.

Apart from my academic engagements, I enjoy playing lawn tennis, and running! In my spare time, I often end up on GitHub (a good replacement to other form of social media).

publications

1. Vision-based Autonomous Landing in Catastrophe-Struck Environments Mayank Mittal, Abhinav Valada, and Wolfram Burgard Workshop on Vision-based Drones: What’s Next?, IROS 2018 [Abs] [arXiv] [Video] [PDF]

   Unmanned Aerial Vehicles (UAVs) equipped with bioradars are a life-saving technology that can enable identification of survivors under collapsed buildings in the aftermath of natural disasters such as earthquakes or gas explosions. However, these UAVs have to be able to autonomously land on debris piles in order to accurately locate the survivors. This problem is extremely challenging as the structure of these debris piles is often unknown and no prior knowledge can be leveraged. In this work, we propose a computationally efficient system that is able to reliably identify safe landing sites and autonomously perform the landing maneuver. Specifically, our algorithm computes costmaps based on several hazard factors including terrain flatness, steepness, depth accuracy and energy consumption information. We first estimate dense candidate landing sites from the resulting costmap and then employ clustering to group neighboring sites into a safe landing region. Finally, a minimum-jerk trajectory is computed for landing considering the surrounding obstacles and the UAV dynamics. We demonstrate the efficacy of our system using experiments from a city scale hyperrealistic simulation environment and in real-world scenarios with collapsed buildings.

projects

Predicting Landing Sites from Aerial Images

DAAD Research Internship

Autonomous Underwater Vehicle (AUV)

Funded by DoRD, IIT Kanpur

Multi- Robot System for Bomb Disposal

Funded by The Boeing Company

other relevant projects

• Verification of Neural Networks using Linear Programming (report)
• Monocular Odometry with Bundle Adjustment (report, video, code)
• Survey on Variational Autoencoders for Bayesian Inference (report)
• Visual Odometry using careful Feature Selection and Tracking (report, code)
• MATLAB based GUI for Motion Planning (code)
• Failure Handling in Swarm of Quadrotors (report)

open source projects

• ROS package for AirSim simulator- in C++ (code)
• ROS package for AirSim simulator- in Python (code)
• ROS package for saving data published from Zed Camera (code)
• ROS package for publishing data from Sparton AHRS8 sensor (code)

teaching

• (Winter 2017: TA, guest lecturer): AE640A: Autonomous Navigation with Mangal Kothari

  • preparing course materials and assignments
  • guest lecturer on system integration using ROS (slides), robot simulation using Gazebo (slides), mathematical foundation for Robotics (slides), and non-parametric filters for localization

tutorials

• (Spring 2019): Hierarchical Reinforcement Learning (slides)
• (Summer 2018): Introduction to Robot Operating System (slides, tutorial, post)
• (Fall 2016): Sensors and Actuators (slides)
• (Fall 2016): Introduction to Robotics (slides)