Our paper Imagine2Servo got accepted to IROS! Will release more information soon!

Our work has been accepted to #IROS2024 🥳 Special shoutout to our collaborator arun kumar singh for fueling the novelty and encouraging progress throughout. #AutonomousDriving Robotics Lab

🚀 Excited to share that our team has submitted 6 groundbreaking papers to #IROS2024! our work on dual-arm manipulation, autonomous driving, trajectory optimization, intelligent visual servoing, semantic-segmentation, and 3D scene understanding. #Robotics #AI

🚀 Check out our paper "QueSTMaps: Queryable Semantic Topological Maps for 3D Scene Understanding" by Yash Mehan , Kumaraditya Gupta, Rohit Jayanti , Ani , Sourav Garg , and Madhava Krishna at #IROS2024 video link: youtube.com/watch?v=g7kv2-… quest-maps.github.io

🚀 Introducing our paper Imagine2Servo: Intelligent Visual Servoing with Diffusion-Driven Goal Generation for Robotic Tasks by Pranjali Pathre ,Gunjan , Mohammad Nomaan Qureshi , Brunda, Samarth Brahmbhatt , K. Madhava Krishna at IROS24 youtu.be/IBxmiVJfbUE brunda02.github.io/RRC/

📢Excited to share that our paper CGDF has been accepted to #IROS2024🎉 📖 Title: Constrained 6-DoF Grasp Generation on Complex Shapes for Improved Dual-Arm Manipulation ✨ CGDF is a grasp diffusion model that generates targeted grasps on object parts efficiently. 🚀 🧵1/n

🎉 Excited to share that our paper "DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions" is accepted to #IROS2024 🤖 📄 Paper link: arxiv.org/pdf/2310.04181 🔗 Website: diffprompter.github.io 💻 Code: github.com/DiffPrompter/d… 🧵👇

RRC paper "Open-Set 3D Semantic Instance Maps for Vision Language Navigation (O3D-SIM)" has been accepted in Advanced Robotics! journal Work led by Laksh Nanwani, Kumaraditya Gupta, Aditya Mathur, & Swayam Agrawal, under guidance of Prof. Madhava Krishna & Dr. A. H. Abdul Hafez.

Revisit Anything: Visual Place Recognition via Image Segment Retrieval Kartik Garg, Sai Shubodh Puligilla, Shishir Kolathaya, Madhava Krishna, Sourav Garg tl;dr: encoding and searching for image segments instead of the whole images arxiv.org/pdf/2409.18049

Places are composed of things. Recognizing & retrieving these things instead of the whole image enables 🧭viewpoint invariance 🖼️semantic interpretability 🔮open-set recognition 🧵on our #ECCV2024 paper: Revisit Anything: Visual Place Recognition via Image Segment Retrieval 👇

Join us for the Second Workshop on Systems and Intelligence for UAV 🚀 an event exploring cutting-edge advancements in UAV technologies! 🗓 Date: 18th & 19th Dec 2024 ⏰ Time: 10:00 AM – 5:00 PM 📍 Venue: IIITH Campus 👉 Register Now: forms.gle/He2kuPwxMjdnk4… #UAVWorkshop #IIITH

🚀 Join us for an inspiring talk by Dr. Shreya Santra on Advanced Robotics for Space Exploration! 🌌🤖 📅 Date: 16th Jan 2025 ⏰ Time: 3:30 pm 📍 Venue: KRB Auditorium, IIITH Explore how cutting-edge robotics is shaping the future of space missions.✨ #SpaceExploration #Robotics

👋Join the Master Trainer Program on Allied UAS Technologies! 📅 March 3-7, 2025, IIIT Hyderabad, Saranga Hall 119, Nilgiri Building 🛠️ Focus Areas: Learning, Vision, Motion Planning for UAS 🔗 Register here: forms.gle/M7RkcQGFCSLEKk… Secure your spot now! 🚀 #UAS #Drones #AI #RRC

🚁 Join the Master Trainer Program on Allied UAS Technologies! 📅 March 3-7, 2025 📍 IIIT Hyderabad, Saranga Hall 119, Nilgiri Building 🛠️ Focus Areas: Learning, Vision, Motion Planning for UAS 🔗 Register here: forms.gle/M7RkcQGFCSLEKk…

Last month, IIIT Hyderabad had the honor of hosting Prof. Aude Billard, President of IEEE RAS and Head of LASA Laboratory, Switzerland, along with Dr. Sudarshan Jayabalan, Chairman of IEEE RAS Hyderabad Section Student Chapter, on January 22, 2025. Here are some memorable moments

CrowdSurfer: Sampling Optimization Augmented with Vector-Quantized Variational AutoEncoder for Dense Crowd Navigation Navigating packed crowds is hard—especially when environments change! Watch CrowdSurfer in action on our Autonomous Wheelchair! 🎥👇 🔗 youtu.be/E2ewPvwEiQM?si…

We improve local planning using generative models (VQVAE + PixelCNN) + inference-time optimization (Priest), achieving: ✅ +40% success rate over DRL-VO ✅ 6% faster travel ✅ No complex human trajectory predictions are needed 📄 Paper: arxiv.org/abs/2409.16011 Laksh Nanwani

💡 Join us for an exciting talk on AI/ML-Assisted Connected & Autonomous Vehicles for 6G and Beyond by Prof. Seshadri Mohan, Professor Emeritus, UA Little Rock! 📅 Date: 21st Feb 202 ⏰ Time: 3:30 PM 📍 Venue: KRB Faculty Meeting Room Don't miss this insightful session! #AI #6G

AdaptBot: Combining LLM with Knowledge Graphs and Human Input for Generic-to-Specific Task Decomposition and Knowledge Refinement at ICRA 2025 Video link: youtu.be/d9qBa6zbkXc Website link: sssshivvvv.github.io/adaptbot/ Shivam Singh ,Karthik Swaminathan ,Nabanita Dash , Ramandeep Singh

🚀 Introducing DA-VIL: Adaptive Dual-Arm Manipulation with RL & Variable Impedance Control! 🤖 DA-VIL integrates Reinforcement Learning & Optimization-based Impedance Control for real-time adaptability. Bollimuntha Shreya Gaurav Singh Faizal Karim Autrio Das saad hashmi #ICRA2025