Pranav Chougule
Ph.D. Researcher | Drexel University

Pranav
Chougule


Robot Learning · Physical AI · Computer Vision · Robotics

Pranav Chougule

I am a Ph.D. researcher at Drexel University working on intelligent robotic systems, robot learning, and AI-driven perception. My research focuses on robotic manipulation, multimodal sensing, and autonomous inspection using vision-language models, imitation learning, reinforcement learning, and sim-to-real transfer.

I develop and investigate robotic systems that use visual and sensor feedback to improve physical interaction, decision-making, and measurement reliability.

Research Focus Areas


01

Robot Learning

Imitation Learning · Reinforcement Learning · Sim-to-Real Transfer

02

Robotic Manipulation & Control

Contact-Rich Manipulation · Force Feedback · Sensor-Guided Control

03

Computer Vision & 3D Perception

Object Detection · Instance Segmentation · 3D Reconstruction · Gaussian Splatting

04

Vision-Language Models & AI

Multimodal Reasoning · Scene Understanding · Contact-Aware Planning

05

Robotics Simulation

NVIDIA Isaac Lab · Isaac Sim · MuJoCo · ROS 2

06

Autonomous Robotic Inspection

Nondestructive Evaluation · Ultrasonic Testing · Multimodal Sensing

Featured Projects


Ongoing Research

Force-Guided Robotic Ultrasonic Inspection Using Imitation and Reinforcement Learning

Robot Learning · Reinforcement Learning · Imitation Learning · Sim-to-Real

Developing learning-based approaches for robotic ultrasonic inspection using force-sensor feedback. Investigating force-guided contact-control policies and sim-to-real transfer using MuJoCo, NVIDIA Isaac Sim, and Isaac Lab.

Technologies

  • Python
  • PyTorch
  • MuJoCo
  • Isaac Sim
  • Isaac Lab
  • ROS 2
  • Force Sensing

Vision-Language AI-Guided Robotic Ultrasonic Inspection

Robotic Perception · Multimodal AI · Computer Vision · Autonomous Inspection

Developed a vision-language-guided robotic inspection framework using Grounding DINO, SAM 2, CLIP, and Qwen2.5-VL-32B for material identification and contact-aware inspection planning.

Achieved 90.3% material-identification accuracy, 90.5% proper-contact selection, and an F1 score of 0.867 in the evaluated tasks.

Technologies

  • UR3e
  • ROS 2
  • Intel RealSense D435i
  • Qwen2.5-VL
  • Grounding DINO
  • SAM 2
  • CLIP
  • Python
  • PyTorch

Publications


Journal Articles

Conference Proceedings

Manuscripts Under Review

Revised Manuscript Under ReviewFirst Author

A Vision-Language Artificial Intelligence System for Contact-Aware Robotic Ultrasonic Inspection of Reclaimed Construction Materials

Chougule, P., et al. (2026).

Expert Systems with Applications

Publication details →
About

About Me

I am a Ph.D. researcher at Drexel University specializing in Robotics, Physical AI, Computer Vision, and Robot Learning.

My research investigates how robots can perceive their environments, interact with physical objects, and use sensor feedback to make intelligent decisions. I develop robotic inspection systems using vision-language models, multimodal perception, force sensing, and autonomous robotic manipulation.

My ongoing research explores imitation learning, reinforcement learning, and sim-to-real transfer for force-guided robotic inspection using MuJoCo, NVIDIA Isaac Sim, and Isaac Lab.

Previously, I earned an M.S. in Robotics and Autonomous Systems from Arizona State University and a B.Tech. in Mechanical Engineering from VJTI Mumbai.

Research Interests: Robot Learning, Embodied AI, Physical AI, Reinforcement Learning, Imitation Learning, Robotic Manipulation, Computer Vision, Multimodal Perception, and Autonomous Robotics.

Degree
Ph.D. Researcher — Drexel University
Research Area
Robotics, Physical AI, Computer Vision & Robot Learning
Primary Research Application
Nondestructive Evaluation (NDE)

Contact


I welcome research collaborations and internship opportunities in robot learning, Physical AI, computer vision, and robotics.