Welcome

Welcome to the homepage of the Learning, Embodied Autonomy, and Forecasting (LEAF) lab, affiliated with the Robotics Institute, Institute for Aerospace Studies, and Department of Computer Science at the University of Toronto. The LEAF lab is led by Prof. Nick Rhinehart.

One of our central aims is general-purpose model-based control: autonomous systems that can be directed to perform a wide range of tasks by combining accurate models of the world with learned objectives. Two capabilities are essential to this vision: forecasting [1,2,3,4,5,6,7,8,9], learning to predict future observations and outcomes from rich sensor data, and reward learning [10,11,12,13,14,15], inferring what humans actually want from demonstrations, preferences, and other feedback. Together, these would allow an agent to simulate what will happen under different actions and select behavior aligned with human intent, without requiring hand-designed rewards or task-specific engineering. Our research draws on imitation learning, reinforcement learning, generative modeling, and information theory, with applications spanning autonomous driving, robot navigation, manipulation, and beyond.

Current research thrusts include: learning transferable world models over high-dimensional sensor data such as LiDAR and occupancy [1,3]; using world models to enable realistic large-scale simulation and efficient planning [1,2]; and learning reward and objective functions from human feedback [10,11] so that autonomous systems can perform complex tasks in alignment with human intent.

News

'OSCAR' accepted as a Spotlight (top 4% of submissions) at CoRL 2026

Sep 10, 2026

Welcome to new graduate students Yang Xu and Akram Khairi!

Sep 8, 2026 University of Toronto

Connaught New Researcher Award

Aug 18, 2026 University of Toronto Robotics Institute

Awarded FASE Joint Seed Grant

Aug 7, 2026

Awarded NSERC Discovery Grant

Jul 3, 2026

Awarded NSERC Alliance Grant with LG Electronics Canada

Jul 1, 2026

Preprint released - UBP2

Jun 17, 2026

See all events

Our team (June, 2026)

Recent publications

OSCAR: Obstacle Survival Curves for Adaptive Robot Navigation.
Hshmat Sahak, Aoran Jiao, Nicholas Rhinehart, Tim Barfoot.
Conference on Robot Learning, (CoRL), 2026.
Spotlight (top 4% of submissions)

Abs PDF Bib

A mobile robot following a graph of known routes can make costly navigation errors when a temporary obstacle blocks a critical edge: waiting too long behind a parked cart wastes time, but immediately rerouting around a person who would move in a few seconds is also inefficient. Standard reactive obstacle avoidance addresses local motion around obstacles, while fixed wait-or-reroute rules ignore how long different obstacle types tend to persist. We propose OSCAR: an adaptive survival-modeling framework for graph-based navigation with temporary blockages. Assuming obstacle class labels are available at encounter time, the robot learns class-conditioned residual clearance-time distributions from online experience, including right-censored observations when it reroutes before observing clearance. These survival models are integrated into a time-dependent graph planner that maintains obstacle memory and computes a patience threshold at each blocked edge: how long to wait before taking an alternate route. The method continuously updates its clearance estimates across episodes and uses them to balance waiting against rerouting. We evaluate the approach in simulation and on a real mobile robot in a university atrium with obstacles including people, chairs, bins, and tubes. In simulation, the learned policy’s time-to-goal converges to within 1% of an oracle with access to ground-truth clearance distributions after fewer than 20 observations per obstacle class, outperforming all heuristic baselines. Real-world deployment confirms that the policy improves online, adapting its patience thresholds from experience across 50 navigation episodes.

@inproceedings{sahak2026oscar,
 author = {Hshmat Sahak and Aoran Jiao and Nicholas Rhinehart and Tim Barfoot},
 booktitle = {Conference on Robot Learning},
 title = {OSCAR: Obstacle Survival Curves for Adaptive Robot Navigation},
 url = {https://arxiv.org/abs/2606.00990},
 year = {2026}
}

Download

Post-Training, Finetuning, and Steering: A Field Guide for Curating Training Data.
Maria Attarian, Yifan Ruan, Claas Voelcker, Chenyang Cao, Amy Zhang, Peter Stone, Nicholas Rhinehart, Igor Gilitschenski.
arXiv:2610.19143, (arXiv), 2026.

PDF Bib

@article{attarian2026posttraining,
  title = {Post-Training, Finetuning, and Steering: A Field Guide for Curating Training Data},
  author = {Attarian, Maria and Ruan, Yifan and Voelcker, Claas and Cao, Chenyang and Zhang, Amy and Stone, Peter and Rhinehart, Nicholas and Gilitschenski, Igor},
  journal = {arXiv preprint arXiv:2610.19143},
  year = {2026},
  doi = {10.48550/arXiv.2610.19143},
  url = {https://arxiv.org/abs/2610.19143}
}

Download

Robotics Machine Learning Reinforcement Learning Manipulation

World-Model Policy Arbiter for Goal-Conditioned Reinforcement Learning.
Junwei Quan, Evgenii Opryshko, Nicholas Rhinehart, Igor Gilitschenski.
arXiv:2610.10932, (arXiv), 2026.

PDF Bib

@article{quan2026wmpa,
  title = {World-Model Policy Arbiter for Goal-Conditioned Reinforcement Learning},
  author = {Quan, Junwei and Opryshko, Evgenii and Rhinehart, Nicholas and Gilitschenski, Igor},
  journal = {arXiv preprint arXiv:2610.10932},
  year = {2026},
  doi = {10.48550/arXiv.2610.10932},
  url = {https://arxiv.org/abs/2610.10932}
}

Download

Reinforcement Learning Machine Learning Model-Based Control Robotics

SPARROW: Survival-POMCP for Adaptive Robot Routing, Observation, and Waiting.
Hshmat Sahak, Aoran Jiao, Nicholas Rhinehart, Timothy D. Barfoot.
arXiv:2609.21008, (arXiv), 2026.

PDF Bib

@article{sahak2026sparrow,
  title = {SPARROW: Survival-POMCP for Adaptive Robot Routing, Observation, and Waiting},
  author = {Sahak, Hshmat and Jiao, Aoran and Rhinehart, Nicholas and Barfoot, Timothy D.},
  journal = {arXiv preprint arXiv:2609.21008},
  year = {2026},
  doi = {10.48550/arXiv.2609.21008},
  url = {https://arxiv.org/abs/2609.21008}
}

Download

Robotics Model-Based Control Offroad Navigation Forecasting

UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning.
Mohamed Nabail, Leo Kaixuan Cheng*, Jingmin Wang*, Nicholas Rhinehart.
arXiv:2606.19328, (arXiv), 2026.

Abs PDF Bib

Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design. However, existing methods typically rely on passive data collection and suffer from poor sample efficiency, especially during the early stages of learning. We introduce a model-based approach that actively directs exploration by jointly reasoning over uncertainties in the reward, dynamics, and value functions. Our method, Uncertainty-Balanced Preference Planning (UBP2), uses ensembles of reward, dynamics, and value function models to evaluate candidate trajectories according to a unified score that combines expected reward, terminal value, and epistemic uncertainty. Planning under this objective yields an explicit tradeoff between exploitation and information acquisition without requiring ad hoc exploration heuristics. Under standard regularity assumptions, we establish sublinear regret guarantees for both finite-horizon and infinite-horizon settings. Empirically, experiments on the Meta-World benchmark show UBP2 achieves substantially higher sample efficiency than model-free preference-based methods and non-optimistic model-based baselines.

@misc{nabail2026ubp2,
 archiveprefix = {arXiv},
 author = {Mohamed Nabail and Leo Cheng and Jingmin Wang and Nicholas Rhinehart},
 eprint = {2606.19328},
 primaryclass = {cs.LG},
 title = {UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning},
 url = {https://arxiv.org/abs/2606.19328},
 year = {2026}
}

Download

Reinforcement Learning Machine Learning Model-Based Control Robotics Reward Learning

See all publications

Our research interests

Fields:

Topics:

Applications:

Other interests:

Supported by