[month] [year]

Poonganam Sri Sai Naga Jyotish – Dual Degree  ECE

Poonganam Sri Sai Naga Jyotish received his MS  in Electronics and Communication Engineering (ECE). His  research work was supervised by Prof. Madhava Krishna K. Here’s a summary of  Poonganam Sri Sai Naga Jyotish’s MS  thesis, Probabilistic Inverse Velocity Obstacles for Navigation under Uncertainty  as explained by him:

Autonomous navigation gained a lot of attention in the past decade.  Motion planning and collision avoidance are the core things that drive these systems.  Several advances resulted in different algorithms to tackle the problem of motion planning and collision avoidance. The crucial question at this stage is how reliable and robust are these systems in a real-life scenario. Recent works in the field have proposed algorithms that account for  the  uncertainties  that  arise  in  a  real-life  scenario.   But  the  work  is  sparse.   In  an attempt to address the reliability and robustness of the navigation frameworks in real-life scenarios, we present two approaches that incorporate the uncertainty in the sensor measurements.

First,  we  present  a  clever  way,  Inverse  Velocity  Obstacle  (IVO),  to  achieve  better collision detection based on the popularly used velocity obstacles.  The proposed method stems  from  the  concept  of  velocity  obstacle  and  can  be  applied  for  both  single-agent and multi-agent systems. It focuses on computing collision-free maneuvers without any knowledge  or  assumption  on  the  position  and  the  velocity  of  the  robot.   We  achieve this by reformulating the velocity obstacle in an ego-centric frame.  This is a significant step  towards  improving  real-time  implementations  of  collision  avoidance  in  dynamic environments  as  there  is  no  dependency  on  state  estimation  techniques  to  infer  the robot’s position and velocity.  We evaluate IVO for both single-agent and multi-agent cases in different scenarios and show its efficacy over the existing formulations.  We also show the real-time scalability of the proposed methodology.

Next, we present a probabilistic variant of the same to handle the state estimation and motion uncertainties that arise due to the other participants of the environment. We present an algorithmic framework that computes collision-free velocities for the robot dynamic and uncertain environments.  We make no assumptions on the nature of the uncertainties and model them as non-parametric probability distributions.  In our Prob-abilistic Inverse Velocity Obstacle (PIVO), we pose the collision-free navigation problemas an optimization problem by reformulating the velocity conditions of IVO as chance constraints that take the uncertainty into account. We also define a lower bound on the confidence of collision avoidance maneuvers that are a result of the optimization.  We demonstrate the algorithm’s ability to generate safe trajectories under highly uncertain environments.