Kaivalya Bakshi

• Doctor of Philosophy
• Software Verification Engineer Flight Controls at Joby Aviation

A team from MIT’s Human Systems Laboratory designed the locomotive HUD as a wide field of view augmented reality head-up display (AR-HUD). The technical feasibility of an AR-HUD was assessed through literature review and hardware tests. To study human factors issues, an AR-HUD prototype was designed, reviewed by experienced engineers, then implemen...

Plenary Symposium (http://www.programmaster.org/PM/PM.nsf/ApprovedAbstracts/288F694650BCD2D28525855E004F9AAE?OpenDocument)

Mean Field Games (MFGs) model a continuum of interacting agents, each of whom aims to minimize a cost that depends upon its own state and control effort, as well as the collective state of the population. Mathematically, MFGs are described by a coupled set of forward and backward in-time partial differential equations for state and control distribu...

Mean Field Game (MFG) systems model a continuum of agents, each of whom aims to minimize a cost that depends upon its own state and control effort, as well as the state of the population. Mathematically, MFGs are described by a coupled set of forward and backward in-time partial differential equations for state and control distributions, respective...

The standard practice in modeling dynamics and optimal control of a large population, ensemble, multi-agent system represented by it's continuum density, is to model individual decision making using local feedback information. In comparison to a closed-loop optimal control scheme, an open-loop strategy, in which a centralized controller broadcasts...

Large-size populations consisting of a continuum of identical and non-cooperative agents with stochastic dynamics are useful in modeling various biological and engineered systems. This paper addresses the stochastic control problem of designing optimal state-feedback controllers which guarantee the closed-loop stability of the stationary density of...

Control of continuous time dynamics with multi-plicative noise is a classic topic in stochastic optimal control. This work addresses the problem of designing infinite horizon optimal controls with stability guarantees for large populations of identical, non-cooperative and non-networked agents with multi-dimensional and nonlinear stochastic dynamic...

Mean Field Games (MFG) have emerged as a promising tool in the analysis of large-scale self-organizing networked systems. The MFG framework provides a non-cooperative game theoretic optimal control description of emergent behavior of large population of rational dynamic agents. Each agents state is driven by optimally controlled dynamics that resul...

Mean Field Games (MFG) have emerged as a viable tool in the analysis of large-scale self-organizing networked systems. In particular, MFGs provide a game-theoretic optimal control interpretation of emergent behavior of non-cooperative agents. The purpose of this paper is to study MFG models in which individual agents obey multidimensional nonlinear...

Optimal control of large-scale multi-agent networked systems which describe social networks, macro-economies, traffic and robot swarms is a topic of interest in engineering, biophysics and economics. A central issue is constructing scalable control-theoretic frameworks when the number of agents is infinite. In this work, we exploit PDE representati...

Large-size populations consisting of a continuum of identical, non-cooperative and non-interacting agents with stochastic dynamics are useful in modeling various biological and engineered systems. This note addresses the problem of designing optimal state-feedback controllers for such systems which guarantee closed-loop stability of the stationary...

Empirically derived continuum models of collective behavior among large populations of dynamic agents are a subject of intense study in several fields, including biology, engineering and finance. We formulate and study a mean-field game model whose behavior mimics an empirically derived non-local homogeneous flocking model for agents with gradient...

Empirically derived continuum models of collective behavior among large populations of dynamic agents are a subject of intense study in several fields, including biology, engineering and finance. We formulate and study a mean-field game model whose behavior mimics an empirically derived non-local homogeneous flocking model for agents with gradient...

Robotics: Science and Systems Early Career Spotlight Talks

While the framework of trajectory optimization based on local approximations of the dynam- ics and value function have been available for over four decades, it was only recently explored in terms of applicable algorithms for efficient control of robotic and biological systems. Although local trajectory optimization is more scalable than global opti...

The success of dynamic programming in solving optimal control problems for stochastic processes has led to the development of many methodologies to execute this class of closed loop control, typically for diffusion processes. However this approach is restricted to controlling the finite dimensional state described by a stochastic dynamic equation....