Publications

2023

1. ICRA 2023

   Learning Augmented, Multi-Robot Long-Horizon Navigation in Partially Mapped Environments

   Khanal, Abhish, and Stein, Gregory J.

   IEEE Conference on Robotics and Automation (ICRA 2023) 2023

   Abs HTML PDF

   We present a novel approach for efficient and reliable goal-directed long-horizon navigation for a multi-robot team in a structured, unknown environment by predicting statistics of unknown space. Building on recent work in learning-augmented model based planning under uncertainty, we introduce a high-level state and action abstraction that lets us approximate the challenging Dec-POMDP into a tractable stochastic MDP. Our Multi-Robot Learning over Subgoals Planner (MR-LSP) guides agents towards coordinated exploration of regions more likely to reach the unseen goal. We demonstrate improvement in cost against other multi-robot strategies; in simulated office-like environments, we show that our approach saves 13.29% (2 robot) and 4.6% (3 robot) average cost versus standard non-learned optimistic planning and a learning-informed baseline.

2. CASE 2023

   Guided Sampling-Based Motion Planning with Dynamics in Unknown Environments

   Khanal, Abhish, Bui, Hoang-Dung, Stein, Gregory J., and Plaku, Erion

   IEEE International Conference on Automation Science and Engineering (CASE) 2023 2023

   Abs HTML PDF

   Despite recent progress improving the efficiency and quality of motion planning, planning collision-free and dynamically-feasible trajectories in partially-mapped environments remains challenging, since constantly replanning as unseen obstacles are revealed during navigation both incurs significant computational expense and can introduce problematic oscillatory behavior. To improve the quality of motion planning in partial maps, this paper develops a framework that augments sampling-based motion planning to leverage a high-level discrete layer and prior solutions to guide motion-tree expansion during replanning, affording both (i) faster planning and (ii) improved solution coherence. Our framework shows significant improvements in runtime and solution distance when compared with other sampling-based motion planners.

2022

1. arxiv

   RRT and RRT* Using Vehicle Dynamics

   Khanal, Abhish

   arxiv 2022

   Abs HTML PDF

   The trajectory derived from RRT and RRT* is zagged. A holonomic drive is able to follow this trajectory. But real-life vehicle which has dynamical constraints cannot follow this trajectory. In this work, we are going to modify the RRT and RRT* algorithm to generate a trajectory that a vehicle with dynamical constraint can follow. The continuous nature of steering control and acceleration control in a real-world vehicle introduces the complexity in its model. To introduce constraint in the vehicle’s motion, while reducing the number of control and hence complexity, we are modeling our vehicle as a Dubins car. A Dubins car has only three controls (turning left, turning right, and moving forward) with a fixed velocity which makes our model simple. We use dubins curve (path that dubins car can follow) to trace the trajectory in RRT and RRT* algorithm.

2021

1. ISCRAM 2020

   Search Disaster Victims using Sound Source Localization

   Khanal, Abhish, Chand, Deepak, Chaudhary, Prakash, Timilsina, Subash, Panday, Sanjeeb Prasad, Shakya, Aman, and Pandey, Rom Kant

   CoRR 2021

   Abs HTML PDF

   Sound Source Localization (SSL) are used to estimate the position of sound sources. Various methods have been used for detecting sound and its localization. This paper presents a system for stationary sound source localization by cubical microphone array consisting of eight microphones placed on four vertical adjacent faces which is mounted on three wheel omni-directional drive for the inspection and monitoring of the disaster victims in disaster areas. The proposed method localizes sound source on a 3D space by grid search method using Generalized Cross Correlation Phase Transform (GCC-PHAT) which is robust when operating in real life scenario where there is lack of visibility. The computed azimuth and elevation angle of victimized human voice are fed to embedded omni-directional drive system which navigates the vehicle automatically towards the stationary sound source.