BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Aerospace Engineering - ECPv6.6.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://aero.iisc.ac.in
X-WR-CALDESC:Events for Department of Aerospace Engineering
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
BEGIN:STANDARD
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
DTSTART:20260101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20260922T103000
DTEND;TZID=Asia/Kolkata:20260922T123000
DTSTAMP:20261011T123848
CREATED:20260921T133040Z
LAST-MODIFIED:20260923T094114Z
UID:10000152-1790073000-1790080200@aero.iisc.ac.in
SUMMARY:Ph.D. (Engg): Development of Learning-based Strategies for Reconnaissance with Multi-Robot Systems
DESCRIPTION:Reconnaissance is the contest for information about a territory: one side tries to observe an asset or a guarded area\, the other tries to deny it. Low-cost drones have made this contest cheap and constant\, and protecting critical infrastructure against it is now a crucial problem\, because an intruder no longer needs to strike a target to threaten it. This thesis develops learning-based strategies for multi-robot reconnaissance from both of its perspectives. In the defense perspective\, a team of defenders must deny reconnaissance of a protected territory by intercepting intruders before they cross its perimeter. In the adversarial perspective\, an agent inside a guarded region must escape to a safe area with the information it has gathered before it is neutralized. Both are hard for the same real-world reasons: opponents arrive from any direction at any time\, so the environment is non-stationary; each robot senses only a limited range\, so the state is partially observed; communication may be unavailable; and the opponent’s numbers and strategy are unknown. Classical game-theoretic and assignment-based methods assume away one or more of these conditions\, which motivates strategies that learn from local observations.\nFor the defense perspective\, the thesis first formulates perimeter defense as a decentralized assignment learning problem and develops the Context-aware Deep Assignment Network (CDAN). Each defender encodes its limited field of view as a spatio-temporal context map of past observations\, the present\, and a predicted future with position uncertainty; pseudo-values around each intruder counter the sparsity of this map and allow a 3D convolutional network\, trained by imitating a centralized solution\, to converge and to be reused by the whole team. CDAN captures about 6% more intruders than the best decentralized baseline (73.4% against 67.5%) and generalizes over team size\, perimeter length\, and intruder speed and maneuvers. Because assignment quality inherits the reliability of the communication channel\, the second contribution\, CARE (Communication-free planning using Adaptive Regions of Engagement)\, resolves the assignment from each defender’s own observations: a defender senses over its full detection radius but commits only within an engagement region set by the distance to its nearest observed teammate\, and drifts its rest position toward the arrival directions it has itself observed. Without a single message\, CARE matches or exceeds communicating baselines over about 200 scenarios and 38\,600 seed-paired episodes\, and is demonstrated on a Crazyflie quadrotor team.\nFor the adversarial perspective\, the third contribution gives the first reinforcement learning formulation of the confinement escape problem\, with a constant-size LiDAR-based state that is independent of the number of pursuers and the shape of the region\, and proposes Scaffolding Reflection based Reinforcement Learning (SR2L)\, in which a simple motion-planner scaffold guides the learner only when its suggestion is clearly better\, so that it can accelerate learning but never damage it. SR2L converges in about half the episodes of standalone actor-critic methods and escapes faster against three pursuit strategies\, with the lowest variance in every case.\nBecause no single learned policy is best under all conditions\, the fourth contribution fuses a pool of pre-trained policies online in a non-stationary environment. Standard multiplicative-weights fusion collapses onto one policy and performs worse than doing nothing. Regularized Reward-aware Online LEarning (ROLE) adapts the fusion weights from the reward of the executed action alone\, without ground truth\, and bounds every weight with an anti-collapse cap. ROLE raises perfect escape runs from 41% for the best single policy to 68% on healthy pools and degrades gracefully when rogue policies contaminate the pool.\nTogether\, these contributions treat reconnaissance in multi-robot systems as one problem seen from two perspectives\, and show that learning from local observations\, with minimal or no information exchange\, can both deny reconnaissance of a protected territory and accomplish it from inside a guarded one. \nSpeaker : Vignesh Gurumurthy \nResearch Supervisor: Prof. Suresh Sundaram \n 
URL:https://aero.iisc.ac.in/event/ph-d-engg-development-of-learning-based-strategies-for-reconnaissance-with-multi-robot-systems/
LOCATION:STC Seminar Hall\, Dept. of Aerospace Engineering
CATEGORIES:Thesis Colloquium / Defence
ATTACH;FMTTYPE=image/jpeg:https://aero.iisc.ac.in/wp-content/uploads/2026/09/Vignesh-Gurumurthy.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20260926T160000
DTEND;TZID=Asia/Kolkata:20260926T170000
DTSTAMP:20261011T123848
CREATED:20260923T060556Z
LAST-MODIFIED:20260923T102930Z
UID:10000153-1790438400-1790442000@aero.iisc.ac.in
SUMMARY:Ph.D. (Engg): A Slotted Wing Configuration for STOL Applications
DESCRIPTION:The rapid development of Urban Air Mobility (UAM) has led to the emergence of electric vertical take-off and landing (eVTOL) aircraft\, with many current concepts relying on tilt-rotor or other complex propulsion-conversion mechanisms to achieve vertical take-off and landing followed by efficient forward flight. While these configurations provide the required operational flexibility\, the mechanical complexity associated with tilting propulsion systems can introduce challenges related to durability\, power efficiency\, system integration\, and flight stability. This thesis explores an alternative approach based on short take-off and landing (STOL) capability\, with the objective of developing a compact\, mechanically simple\, and aerodynamically efficient wing configuration that can reduce the dependence on such complex mechanisms. The proposed design is CFD based and the required computations have been carried out using the CFD solver HiFUN. All computations have been performed using standard SA turbulence model. The propellers are simulated using varying levels of fidelity available in the solver\, such as the Blade Element Method and sliding mesh simulations. Moving mesh capability available in the solver is made use of in simulating synthetic jets.\nA novel fixed-wing configuration is developed specifically for STOL operation in the context of urban air mobility. Instead of relying on conventional high-lift devices\, the proposed configuration combines a highly cambered wing\, distributed propulsion\, and active flow control to achieve the high lift required during take-off and landing. A NACA four-digit formulation is used to define the airfoil\, with an unconventionally high camber and a slot introduced at the location of maximum camber. To maintain vehicle compactness while improving aerodynamic efficiency\, a low aspect-ratio wing with optimized end plates is employed. The influence of end-plate size on the aerodynamic performance is investigated\, showing a progressive reduction in trailing-vortex strength and associated induced effects on lift and drag with increasing end-plate size. Based on the investigated configurations\, an end plate with a width equal to 20% of the wing aerodynamic chord is selected.\nDistributed propulsion is subsequently integrated into the wing configuration to exploit propeller slipstream effects during STOL operation. An enhanced actuator-disc model\, coupled with blade-element analysis\, is used to represent the propellers\, with a NACA 640 four-bladed propeller selected for the study. The propeller thrust requirements are determined from the take-off drag of the unpowered wing and distributed among four equally spaced propellers. The interaction between an individual propeller and the wing is first investigated to determine the optimum propeller location. The resulting slipstream–wing interaction substantially increases the wing lift\, thereby reducing the required take-off velocity. The complete powered configuration is then investigated using high-fidelity sliding-mesh simulations with counter-rotating propellers arranged on either side of the wing. \nThe high camber required to achieve the desired lift characteristics introduces a separation bubble in the rear portion of the wing downstream of the slot. To address this limitation without introducing conventional high-lift mechanisms\, a zero-net-mass-flux active flow-control system based on synthetic jets is incorporated. A dynamic-mesh methodology is first validated against the NASA Langley Research Center standard hump test case with oscillatory control. The validated methodology is then used to establish the actuator momentum coefficient and excitation frequency. To reduce the computational cost of the full-wing simulations\, an unsteady boundary-condition model is developed and validated and subsequently employed to investigate the effectiveness of synthetic-jet actuation in suppressing the separation bubble and improving the aerodynamic performance of the wing. Discrete synthetic-jet slits are positioned between the propeller slipstreams\, allowing flow control to be concentrated in regions outside the primary propeller wakes while reducing the additional power requirement.\nOverall\, the thesis demonstrates the feasibility of combining fixed-wing STOL aerodynamics\, distributed propulsion\, and localized active flow control as an alternative pathway for compact urban air-mobility vehicles. \n  \nSpeaker : S Amsha \nResearch Supervisor : N. Balakrishnan
URL:https://aero.iisc.ac.in/event/ph-d-engg-a-slotted-wing-configuration-for-stol-applications/
LOCATION:Online
CATEGORIES:Thesis Colloquium / Defence
ATTACH;FMTTYPE=image/jpeg:https://aero.iisc.ac.in/wp-content/uploads/2026/09/S-Amsha.jpg
END:VEVENT
END:VCALENDAR