Homanga Bharadhwaj

hbharadh at cs dot cmu dot edu

I am a final-year PhD student in the Robotics Institute, School of Computer Science, Carnegie Mellon University advised by Abhinav Gupta and Shubham Tulsiani. I was recently a student researcher at Google DeepMind in Mountain View. Previously I was a visiting researcher at FAIR, Meta AI in Pittsburgh for two years during my PhD. I am engaged in the quest for understanding intelligence by trying to simulate it. Although this quest has kept me fully occupied for the past several years, I also paint, and have a Bachelor of Arts degree in Fine Arts. Some of my paintings can be found here.

Bio  /  Email  /  Github  /  GScholar  /  Twitter  /  Name  /  Art  /  Poem

refresh page to see homangas in diverse environments
Education / Employment

News/Highlights

  • [2024] Open-X: Best Conference Paper Award at ICRA 2024
  • [2024] HOPMan: Best Paper in Robot Manipulation Finalist at ICRA 2024
  • [2023] RoboAgent: Outstanding Presentation Award at the Robot Learning Workshop, NeurIPS 2023
  • [2023] Our sample-efficient universal manipulation research was covered by TechCrunch, ACM, IEEE
  • [2021] Our research on safe exploration for robotics was convered by VentureBeat

If you have any questions / want to collaborate, feel free to send me an email! I am always excited to learn more by talking with people.

For junior graduate/undergraduate students: I commit 40 minutes every week for chatting about anything related to career guidance, life goals, and research on AI and adjacent areas. In case of multiple requests, I'll prioritize meetings with students from under-represented groups. If such a meeting would be helpful, feel free to email me for a 20 min. or a 40 min. slot. and include "HELLOHOMANGA" in the subject of the email.

Research

I'm interested in developing embodied AI systems capable of helping us in the humdrum of everyday activities within messy rooms, offices, and kitchens, in a reliable, compliant, and scalable manner without requiring significant robot-specific data collection and task-specific heuristics. A major thrust of my research is on combining robot-specific data with predictive planning from diverse web videos such as YouTube clips of humans doing daily chores, for developing robust robot learning algorithms that are sample-efficient, safety-aware through constraint satisfaction, and that can scale across diverse (unseen) real-world tasks. I have eclectic research interests, and have also worked on robustness in machine learning, and improving sample efficiency, and representations in reinforcement learning.

In my research, I conduct experiments across robot embodiments for demonstrating generalization of policies to unseen tasks including those involving manipulation of completely unseen object types with novel motions. Here are some glimpses of common goal/langauge-conditioned policy deployments in unseen offices and kitchens:

  

  
Glimpse of robot deployment results from my works (Gen2Act, Track2Act, HOPMan, RoboAgent). Each robot is controlled with a single goal-conditioned policy where the goal is either an image or a language description specifying the task, and deployed in unseen offices and kitchens.
Most significant bits
Robotics / Reinforcement Learning
Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation
Homanga Bharadhwaj, Debidatta Dwibedi, Abhinav Gupta, Shubham Tulsiani, Carl Doersch, Ted Xiao, Dhruv Shah, Fei Xia, Dorsa Sadigh, Sean Kirmani
arXiv 2024  
paper website video  

Casting language-conditioned manipulation as human video generation followed by closed-loop policy execution conditioned on the generated video enables solving diverse real-world tasks involving object/motion types unseen in the robot dataset.

Track2Act: Predicting Point Tracks from Internet Videos Enables Diverse Zero-shot Manipulation
Homanga Bharadhwaj, Roozbeh Mottaghi*, Abhinav Gupta*, Shubham Tulsiani*
ECCV 2024  
paper website  

We can train a model for embodiment-agnostic point track prediction from web videos combined with embodiment-specific residual policy learning for diverse real-world manipulation in everyday office and kitchen scenes. The resulting goal-conditioned policy can be zero-shot deployed in unseen scenarios.

RoboAgent: Towards Sample Efficient Robot Manipulation with Semantic Augmentations and Action Chunking
Homanga Bharadhwaj*, Jay Vakil*, Mohit Sharma*, Abhinav Gupta, Shubham Tulsiani, Vikash Kumar
ICRA 2024  
Robot Learning Workshop, NeurIPS 2023 (Outstanding Presentation Award)  
paper website data  

We can develop a single robot manipulation agent capable of over 38 tasks across 100s of scenes, through semantic augmentations for multiplying data, and action chunking transformers for fitting the multi-modal data distribution.

Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans
Homanga Bharadhwaj, Abhinav Gupta*, Vikash Kumar*, Shubham Tulsiani*
ICRA 2024 (Best Paper in Robot Manipulation Finalist)  
paper website video  

Learning interaction plans from diverse passive human videos on the web, followed by translation to robotic embodiments can help develop a single goal-conditioned policy that scales to over 100 diverse tasks in unseen scenarios, including real kitchens and offices.

Zero-Shot Robot Manipulation from Passive Human Videos
Homanga Bharadhwaj, Abhinav Gupta, Shubham Tulsiani*, Vikash Kumar*
Pretraining for Robotics Workshop, ICRA 2023 (Spotlight Talk)  
RAP4 Workshop, ICRA 2023 (Spotlight Talk)  
paper website

Learning to predict plausible hand motion trajectories from passive human videos on the web, followed by transformation of the predictions to a robot's frame of reference enables zero-shot coarse-manipulation with real-world objects.

CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning
Mandi Zhao, Homanga Bharadhwaj, Vincent Moens, Shuran Song, Aravind Rajeswaran, Vikash Kumar
Pretraining for Robotics Workshop, CoRL 2022  
paper website

Through effective augmentations enabled by recent advances in generative modeling, we can develop a framework for learning robust manipulation policies capable of solving multiple tasks in diverse real-world scenes.

Visual Affordance Prediction for Guiding Robot Exploration
Homanga Bharadhwaj, Abhinav Gupta, Shubham Tulsiani
ICRA 2023 paper website  

We can enable goal-directed robot exploration in the real world by learning an affordance model to predict plausible future frames given an initial image from passive human interaction videos, in combination with self-behavior cloning for policy learning.

Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective
Raj Ghugare, Homanga Bharadhwaj, Benjamin Eysenbach, Sergey Levine, Ruslan Salakhutdinov
ICLR 2023 paper website reviews  

We can learn a latent-space model, and a policy for RL jointly through a single objective, by deriving a lower-bound to the overall RL objective

Information Prioritization Through Empowerment in Visual Model-based RL
Homanga Bharadhwaj, Mohammad Babaeizadeh,Dumitru Erhan, Sergey Levine
ICLR 2022 paper website reviews  

Empowerment along with mutual information maximization helps learn functionally relevant factors in visual model-based RL, especially in environments with complex visual distractors.

Conservative Safety Critics for Exploration
Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, Animesh Garg
ICLR 2021 paper website reviews  

Training a critic to make conservative safety estimates by over-estimating how unsafe a particular state is, can help significantly minimize the number of catastrophic failures in constrained RL

Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos
Haoyu Xiong, Quanzhou Li, Yun-Chun Chen, Homanga Bharadhwaj, Samarth Sinha, Animesh Garg
IROS 2021  
paper website  

We can learn to imitate human videos for manipulation by extracting task-agnostic keypoints to define an imitation objective that abstracts out aspects of the human/robot embodiment gap.

Latent Skill Exploration for Planning and Transfer
Kevin (Cheng) Xie*, Homanga Bharadhwaj*, Danijar Hafner, Animesh Garg, Florian Shkurti
ICLR 2021 paper website reviews  

Combining online planning of high level skills with an amortized low level policy can improve sample-efficiency of model-based RL for solving complex tasks, and transferring across tasks with similar dynamics.

Model-Predictive Planning via Cross-Entropy and Gradient-Based Optimization
Homanga Bharadhwaj*, Kevin (Cheng) Xie*, Florian Shkurti
L4DC, 2020 paper code reviews  

Updating the top action sequences identified by CEM through a few gradient steps helps improve sample efficiency and performance of planning in Model-based RL

Continual Model-Based Reinforcement Learning with Hypernetworks
Philip Huang, Kevin (Cheng) Xie, Homanga Bharadhwaj, Florian Shkurti
ICRA, 2021 and Deep RL Workshop (NeurIPS 20) paper code video  

Task-conditioned hypernetworks can be used to continually adapt to varying environment dynamics, with a limited replay buffer in lifelong robot learning

LEAF: Latent Exploration Along the Frontier
Homanga Bharadhwaj, Animesh Garg, Florian Shkurti
ICRA, 2021 paper  

Keeping track of the currently reachable frontier of states, and executing a deterministic policy to reach the frontier followed by a stochastic policy beyond, can help facilitate principled exploration in RL

D2RL: Deep Dense Architectures in Reinforcement Learning
Samarth Sinha*, Homanga Bharadhwaj*, Aravind Srinivas, Animesh Garg
Deep RL Workshop (NeurIPS 20) paper blog code reviews  

Introducing skip connections in the policy and Q function neural networks can improve sample efficiency of reinforcement learning algorithms across different continuous control environments

A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies
Homanga Bharadhwaj*, Zihan Wang*, Yoshua Bengio, Liam Paull
ICRA 2019 paper video  

Adversarial domain adaptation can be used for training a gradient descent based planner in simulation and transferrring the learned model to a real navigation environment.

Vision / Representation Learning
DIBS: Diversity inducing Information Bottleneck in Model Ensembles
Samarth Sinha*, Homanga Bharadhwaj*, Anirudh Goyal, Hugo Larochelle, Animesh Garg, Florian Shkurti
AAAI, 2021 (and ICML-UDL, 2020) paper  

Explicitly maximizing diversity in ensembles through adversarial learning helps improve generalization, transfer, and uncertainty estimation

DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning
Timo Milbich*, Karsten Roth*, Homanga Bharadhwaj, Samarth Sinha, Yoshua Bengio, Bjorn Ommer, Joseph Paul Cohen
ECCV, 2020 paper code  

Appropriately augmenting training with multiple complimentary tasks can improve generalization in Deep Metric Learning.

Generalized Adversarially Learned Inference
Yatin Dandi, Homanga Bharadhwaj, Abhishek Kumar, Piyush Rai,
AAAI, 2021 paper code  

Adversarially learned inference can be generalized to incorporate multiple layers of feedback through reconstructions, self-supervision, and learned knowledge.

A Generative Framework for Zero Shot Learning with Adversarial Domain Adaptation
Varun Khare, Divyat Mahajan, Homanga Bharadhwaj, VK Verma, Piyush Rai
WACV, 2020 paper code  

Adversarial Domain Adaptation appropriately incorporated in a Generative Zero Shot Learning model can help minimize domain shift and significantly enhance generalization on the unseen test classes

Auditing AI models for Verified Deployment under Semantic Specifications
Homanga Bharadhwaj, De-An Huang, Chaowei Xiao, Anima Anandkumar Animesh Garg
under review paper blog  

Auditing deep-learning models for human-interpretable specifications, prior to deployment is important in preventing unintended consequences. These specifications can be obtained by considering variations in an interpretable latent space of a generative model.

RecGAN: Recurrent Generative Adversarial Networks for Recommendation Systems
Homanga Bharadhwaj, Homin Park, Brian Y. Lim
RecSys, 2018 paper

Recurrent Neural Network based Generative Adversarial Networks can learn to effectively model the latent preference trends of users in time-series recommendation.

My tryst with HCI research
De-anonymization of authors through arXiv submissions during double-blind peer review
Homanga Bharadhwaj, Dylan Turpin, Animesh Garg, Ashton Anderson
arXiv, 2020 paper blog  

In an analysis of ICLR 2020 and 2019 papers, we find positive correlation between releasing preprints on arXiv and acceptance rates of papers by well-known authors. For well known authors, acceptance rates for papers with arxiv preprint are higher than those without preprints released during review.

New tab page recommendations cause a strong suppression of exploratory web browsing behaviors
Homanga Bharadhwaj, Nisheeth Srivastava
WebSci, 2019

Passive website recommendations embedded in the new tab displays of browsers (that recommend based on frecency) inhibit peoples' propensity to visit diverse information sources on the internet

My freshman year dabble with Quantum Entanglement

Phase matching in Spontaneous Parametric Down Conversion
Suman Karan, Shaurya Aarav, Homanga Bharadhwaj, Lavanya Taneja, Girish Kulkarni, Anand K Jha
Journal of Optics (Accepted 2020)

Spontaneous Parametric Down Conversion is used to generate entangled photon pairs. SPDC can be studies through the lens of Wave Optics by making some simplifying theoretical assumptions without compromising on empirical results. Also, a simulation for SPDC can be conveniently designed, given the assumptions.


I love his website design.

Visitor Hit Counter