BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.3.7.4//EN
TZID:Asia/Kolkata
X-WR-TIMEZONE:Asia/Kolkata
BEGIN:VEVENT
UID:208@cds.iisc.ac.in
DTSTART;TZID=Asia/Kolkata:20260707T150000
DTEND;TZID=Asia/Kolkata:20260707T160000
DTSTAMP:20260702T045533Z
URL:https://cds.iisc.ac.in/events/m-tech-research-thesis-colloquium-102-cd
 s-07-july-2026-reliable-autonomous-uav-programming-through-structured-llm-
 guided-middleware/
SUMMARY:M.Tech Research Thesis {Colloquium}: 102: CDS: 07\, July 2026 “Re
 liable Autonomous UAV Programming through Structured LLM-guided Middleware
 ”
DESCRIPTION:DEPARTMENT OF COMPUTATIONAL AND DATA SCIENCES\nM.Tech Research 
 Thesis {Colloquium}\n\n\n\nSpeaker: Mr. Kautuk Astu\nS.R. Number: 06-18-01
 -10-22-24-1-25480\nTitle: “Reliable Autonomous UAV Programming through S
 tructured LLM-guided Middleware”\nResearch Supervisor: Prof. Yogesh Simm
 han\nDate &amp\; Time : July 07\, 2026 (Tuesday)\, 15:00 PM\nVenue : #102\
 , CDS Seminar Hall\n\n\n\nABSTRACT\nRecent advances in Unmanned Aerial Veh
 icles (UAVs)\, edge computing and AI have enabled aerial applications in p
 recision agriculture\, infrastructure inspection\, disaster response\, and
  urban services. However\, developing such applications remains challengin
 g due to the tight coupling of navigation\, sensing\, analytics\, and edge
 -cloud resources. The existing frameworks still rely on low-level APIs tha
 t require manual integration of mission logic\, scheduling\, and deploymen
 t. Also\, despite Large Language Models (LLMs) offering new opportunities 
 for automating drone application development\, the area remains underexplo
 red due to lack of reliability in mission critical systems. This thesis ad
 vances the vision of Drone-as-a-Service (DaaS) through three complementary
  contributions: (1) AeroDaaS\, extending a service-oriented programming fr
 amework and runtime\, (2) AeroGen\, for LLM-assisted generation of drone p
 rograms and automated execution\, and (3) AeroEval\, a mission validation 
 framework for LLM-generated applications. Together\, these contributions e
 stablish an end-to-end ecosystem for reliable autonomous aerial applicatio
 ns across heterogeneous drones. To address the challenge of programmabilit
 y and runtime support for DaaS spanning edge and cloud environments\, we e
 xtend prior work on AeroDaaS to support five representative mission patter
 ns and develop a service-oriented programming framework with reusable APIs
 . It includes modular analytics and trajectory scheduling policies\, and a
  portable containerized runtime for heterogeneous UAV platforms and simula
 tors.\n\nOur evaluation of seven representative applications and schedulin
 g algorithms demonstrates concise application code (≤ 40 lines of co
 de)\, low runtime overhead (≤20 ms/frame)\, and low memory footprint
  (under 1 GB). AeroDaaS serves as an efficient programming framework and p
 latform for aerial DaaS applications. Building upon this\, we address the 
 gap of code automation through AeroGen. This leverages LLMs to automatical
 ly generate DaaS application code from natural-language mission descriptio
 ns. It combines the AeroDaaS APIs with structured guardrail prompting that
  encodes API specifications\, operational constraints and flight rules to 
 generate deployment-ready drone programs. In evaluations performed across 
 20 navigation tasks and 5 analytical missions in simulation and real-world
  deployments\, AeroGen achieves 100% single-pass success while consistentl
 y satisfying mission objectives. These demonstrate that structured prompti
 ng and well-designed programming abstractions significantly improve the re
 liability of AI-generated drone applications and automation. Finally\, to 
 improve reliability of generated missions we propose AeroEval\, a middlewa
 re that enhances the reliability of AeroGen generated code through closed-
 loop multi-stage validation. It performs static pre-flight analysis like s
 yntax correctness\, API compliance and intent verification\, further verif
 ied by simulation-based trajectory validation. Evaluation on 20 navigation
  and 5 analytical missions improves navigation success from 55% to 95% and
  analytical mission success by over 50% compared to AeroGen across multipl
 e iterations\, while revealing illusion of correctness in generated progra
 ms. These show that automated mission validation can result in reliable AI
 -assisted DaaS systems.\n\nCollectively\, these contributions establish an
  end-to-end Drone-as-a-Service ecosystem spanning programming\, AI-assiste
 d application generation and mission validation. Together\, they bridge th
 e gap between high-level mission specifications and dependable real-world 
 deployment of autonomous aerial applications.\n\n\n\nALL ARE WELCOME
CATEGORIES:MTech Research Thesis Colloquium
END:VEVENT
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
X-LIC-LOCATION:Asia/Kolkata
BEGIN:STANDARD
DTSTART:20250707T150000
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR