Dvij Kalaria

First-year PhD student

EECS, UC Berkeley

Biography

Hi! I am Dvij Kalaria, a first-year EECS PhD student at UC Berkeley affiliated with Berkeley AI Research (BAIR) advised by Prof. Shankar Sastry.

Previously I was a MS Robotics student at CMU LeCAR lab and DRIVE lab, working with Professor Guanya Shi and John M. Dolan. For my undergraduate thesis, I was co-advised by Prof. Partha Pratim Chakrabarti and Prof. Aritra Hazra

Broadly, I am interested in Agile robots 🦾 🦿 🏎️ that operate at their limits and can rapidly adapt to unknown scenarios. Currently, I am focused on marying game theory with real-time robots such that they can play sports like table tennis, and can collaborate with humans in whole body tasks like lifting and moving around heavy objects.

From 2022 to 2024 I led vehicle dynamics team of AI Racing Tech 🏎️, a multi-million $ autonomous racing research project in UCB, CMU and UCSD. I deployed real-world robot learning on F1-level self-driving race cars at 160 MPH. We are the top U.S. team in the Indy Autonomous Challenge.

resume / CV (elaborate).

Interests

Agile robots
Embodied AI
Reinforcement Learning
Adaptive Learning-based Control
Computer Vision

Education

EECS PhD, 2024-

BAIR, UC Berkeley
MS in Robotics (MSR), 2022-2024

Robotics Institute, Carnegie Mellon University (CMU)
B.Tech in Computer Science, 2018-2022

Indian Institute of Technology Kharagpur

Publications

Agile Mobility with Rapid Online Adaptation via Meta-learning and Uncertainty-aware MPPI

Modern non-linear model-based controllers require an accurate physics model and model parameters to be able to control mobile robots at …

Dvij Kalaria, Haoru Xue, Wenli Xiao, Tony Tao, Guanya Shi, John Dolan, -Under review, ICRA 2025

Agile Mobility with Rapid Online Adaptation via Meta-learning and Uncertainty-aware MPPI

AnyCar to Anywhere Learning Universal Dynamics Model for Agile and Adaptive Mobility

Recent works in the robot learning community have successfully introduced generalist models capable of controlling various robot …

Wenli Xiao, Haoru Xue, Tony Tao, Dvij Kalaria, Guanya Shi, John Dolan, -Under review, ICRA 2025

AnyCar to Anywhere Learning Universal Dynamics Model for Agile and Adaptive Mobility

Delay-aware Robust Control for Safe Autonomous Driving and Racing

Delays endanger safety of autonomous systems operating in a rapidly changing environment, such as nondeterministic surrounding traffic …

Dvij Kalaria, Qin Lin, John M. Dolan, -*Transactions on Intelligent Transportation Systems (T-ITS)*

Delay-aware Robust Control for Safe Autonomous Driving and Racing

Towards Optimal Head-to-Head Autonomous Racing with Curriculum Reinforcement Learning

Autonomous head-to-head racing presents a formidable challenge, demanding vehicles to operate at the limits of friction and handling in …

Dvij Kalaria, Qin Lin, John Dolan, -Presented at MADGames workshop, IROS 2023 and under review, RLC 2024

Towards Optimal Head-to-Head Autonomous Racing with Curriculum Reinforcement Learning

Adaptive Planning and Control with Time-Varying Tire Models for Autonomous Racing Using Extreme Learning Machine

Autonomous racing is a challenging problem, as the vehicle needs to operate at the friction or handling limits in order to achieve …

Dvij Kalaria, Qin Lin, John M Dolan, -Accepted, ICRA 2024

Adaptive Planning and Control with Time-Varying Tire Models for Autonomous Racing Using Extreme Learning Machine

Disturbance Observer-based Control Barrier Functions with Residual Model Learning for Safe Reinforcement Learning

Reinforcement learning (RL) agents need to explore their environment to learn optimal behaviors and achieve maximum rewards. However, …

Dvij Kalaria, Qin Lin, John M Dolan, -Under review, ICRA 2025

Disturbance Observer-based Control Barrier Functions with Residual Model Learning for Safe Reinforcement Learning

Delay-aware Robust Control for Safe Autonomous Driving

With the advancement of affordable self-driving vehicles using complicated nonlinear optimization but limited computation resources, …

Dvij Kalaria, Qin Lin, John M. Dolan, -Accepted at *IEEE Intelligent Vehicles Symposium 2022 (oral)*

Delay-aware Robust Control for Safe Autonomous Driving

Detecting Adversaries, yet Faltering to Noise? Leveraging Conditional Variational AutoEncoders for Adversary Detection in the Presence of Noisy Images

With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their …

Dvij Kalaria, Aritra Hazra, Partha Pratim Chakrabarti, -Accepted at 'Workshop on Adversarial Machine Learning and Beyond, AAAI 2022'

Detecting Adversaries, yet Faltering to Noise? Leveraging Conditional Variational AutoEncoders for Adversary Detection in the Presence of Noisy Images

Online Adaptive Compensation for Model Uncertainty Using Extreme Learning Machine-based Control Barrier Functions

A control barrier functions-based quadratic programming (CBF-QP) method has emerged as a controller synthesis tool to assure safety of …

Dvij Kalaria, Qin Lin, John Dolan, -IROS 2022

Online Adaptive Compensation for Model Uncertainty Using Extreme Learning Machine-based Control Barrier Functions

Towards Adversarial Purification using Denoising AutoEncoders

With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their …

Dvij Kalaria, Aritra Hazra, Partha Pratim Chakrabarti, -Accepted at 'MLSW workshop, NeurIPS 2022'

Towards Adversarial Purification using Denoising AutoEncoders

Towards Safety Assured End-to-End Vision-Based Control for Autonomous Racing

Autonomous car racing is a challenging task, as it requires precise applications of control while the vehicle is operating at cornering …

Dvij Kalaria, Qin Lin, John M. Dolan, -IFAC World Congress 2023

Towards Safety Assured End-to-End Vision-Based Control for Autonomous Racing

Local NMPC on Global Optimised Path for Autonomous Racing

The paper presents a strategy for the control of an autonomous racing car on a pre-mapped track. Using a dynamic model of the vehicle, …

Dvij Kalaria, Parv Maheshwari, Animesh Jha, Arnesh Kumar Issar, Debashish Chakravarty, Sohel Anwar, Andres Tovar, -Accepted at 'Opportunities and Challenges in Autonomous Racing' worskshop, ICRA 2021