Generative Models
All Publication Topics
Autonomous Driving
Autonomous Exploration
Benchmarks
Compression
Computer Vision
First-Person Video
Forecasting
Generative Models
Imitation Learning
Intrinsic Control
Machine Learning
Manipulation
Model-Based Control
Offroad Navigation
Paper Award
Reinforcement Learning
Reward Learning
Robotics
Social Navigation
QPILOTS: Efficient Test-Time Q-Steering for Flow Policies.
arXiv:2606.14801, (arXiv), 2026.
arXiv:2606.14801, (arXiv), 2026.
Flow-matching and diffusion policies are expressive action generators, but optimizing them with temporal-difference reinforcement learning (RL) remains difficult. Effective policy extraction requires exploiting the critic’s action gradient, yet directly backpropagating this signal through a multi-step denoising process can be numerically unstable. Existing methods work around this either by discarding gradient information, distilling the policy into a simpler one-step actor, or repeatedly fine-tuning the denoising policy as the critic improves. We propose QPILOTS, a method that leaves the original policy unmodified and steers the denoising process at inference time. At each denoising step, instead of evaluating the critic on the noisy intermediate action where critic predictions are unreliable, we first project that intermediate state to an estimate of the final clean action and compute the critic gradient there. We introduce two variants: QPILOTS-U uses a fast single-point approximation, while QPILOTS-M draws differentiable posterior samples via a learned auxiliary network. On a standard offline-to-online RL benchmark, QPILOTS achieves the best aggregate performance, reaching an average success rate of 90% across 50 tasks. We also apply QPILOTS to steer a large, frozen, pretrained Vision-Language Action (VLA) foundation model, outperforming or matching prior inference-time approaches across six manipulation tasks in simulation.
@article{ruan2026qpilots,
title = {QPILOTS: Efficient Test-Time Q-Steering for Flow Policies},
author = {Ruan, Yifan and Cao, Chenyang and Burger, Andreas and Pesaranghader, Ali and Kamali, Kaveh and Kim, Jaehong and Vijaykumar, Nandita and Aspuru-Guzik, Alan and Gilitschenski, Igor and Rhinehart, Nicholas},
journal = {arXiv preprint arXiv:2606.14801},
year = {2026},
doi = {10.48550/arXiv.2606.14801},
url = {https://arxiv.org/abs/2606.14801}
}
OccSim: Multi-kilometer Simulation with Long-horizon Occupancy World Models.
arXiv:2603.28887, (arXiv), 2026.
arXiv:2603.28887, (arXiv), 2026.
Data-driven autonomous driving simulation has long been constrained by its heavy reliance on pre-recorded driving logs or spatial priors, such as HD maps. This fundamental dependency severely limits scalability, restricting open-ended generation capabilities to the finite scale of existing collected datasets. To break this bottleneck, we present OccSim, the first occupancy world model-driven 3D simulator. OccSim obviates the requirement for continuous logs or HD maps; conditioned only on a single initial frame and a sequence of future ego-actions, it can stably generate over 3,000 continuous frames, enabling the continuous construction of large-scale 3D occupancy maps spanning over 4 kilometers for simulation. This represents an >80x improvement in stable generation length over previous state-of-the-art occupancy world models. OccSim is powered by two modules: W-DiT based static occupancy world model and the Layout Generator. W-DiT handles the ultra-long-horizon generation of static environments by explicitly introducing known rigid transformations in architecture design, while the Layout Generator populates the dynamic foreground with reactive agents based on the synthesized road topology. With these designs, OccSim can synthesize massive, diverse simulation streams. Extensive experiments demonstrate its downstream utility: data collected directly from OccSim can pre-train 4D semantic occupancy forecasting models to achieve up to 67% zero-shot performance on unseen data, outperforming previous asset-based simulator by 11%. When scaling the OccSim dataset to 5x the size, the zero-shot performance increases to about 74%, while the improvement over asset-based simulators expands to 22.1%.
@article{liu2026occsim,
title = {OccSim: Multi-kilometer Simulation with Long-horizon Occupancy World Models},
author = {Liu, Tianran and Zhao, Shengwen and Pourkeshavarz, Mozhgan and Li, Weican and Rhinehart, Nicholas},
journal = {arXiv preprint arXiv:2603.28887},
year = {2026},
doi = {10.48550/arXiv.2603.28887},
url = {https://arxiv.org/abs/2603.28887}
}
AutoWorld: Scaling Multi-Agent Traffic Simulation with Self-Supervised World Models.
arXiv:2603.28963, (arXiv), 2026.
arXiv:2603.28963, (arXiv), 2026.
Multi-agent traffic simulation is central to developing and testing autonomous driving systems. Recent data-driven simulators have achieved promising results, but rely heavily on supervised learning from labeled trajectories or semantic annotations, making it costly to scale their performance. Meanwhile, large amounts of unlabeled sensor data can be collected at scale but remain largely unused by existing traffic simulation frameworks. This raises a key question: How can a method harness unlabeled data to improve traffic simulation performance? In this work, we propose AutoWorld, a traffic simulation framework that employs a world model learned from unlabeled occupancy representations of LiDAR data. Given world model samples, AutoWorld constructs a coarse-to-fine predictive scene context as input to a multi-agent motion generation model. To promote sample diversity, AutoWorld uses a cascaded Determinantal Point Process framework to guide the sampling processes of both the world model and the motion model. Furthermore, we designed a motion-aware latent supervision objective that enhances AutoWorld’s representation of scene dynamics. Experiments on the WOSAC benchmark show that AutoWorld ranks first on the leaderboard according to the primary Realism Meta Metric (RMM). We further show that simulation performance consistently improves with the inclusion of unlabeled LiDAR data, and study the efficacy of each component with ablations. Our method paves the way for scaling traffic simulation realism without additional labeling. Our project page contains additional visualizations and released code.
@article{pourkeshavarz2026autoworld,
title = {AutoWorld: Scaling Multi-Agent Traffic Simulation with Self-Supervised World Models},
author = {Pourkeshavarz, Mozhgan and Liu, Tianran and Rhinehart, Nicholas},
journal = {arXiv preprint arXiv:2603.28963},
year = {2026},
doi = {10.48550/arXiv.2603.28963},
url = {https://arxiv.org/abs/2603.28963}
}
Towards foundational LiDAR world models with efficient latent flow matching.
Advances in Neural Information Processing Systems, (NeurIPS), 2025.
Advances in Neural Information Processing Systems, (NeurIPS), 2025.
LiDAR-based world models offer more structured and geometry-aware representations than their image-based counterparts. However, existing LiDAR world models are narrowly trained; each model excels only in the domain for which it was built. This raises a critical question: can we develop LiDAR world models that exhibit strong transferability across multiple domains? To answer this, we conduct the first systematic domain transfer study across three demanding scenarios: (i) outdoor to indoor generalization, (ii) sparse- to dense-beam adaptation, and (iii) non-semantic to semantic transfer. Given different amounts of fine-tuning data, our experiments show that a single pretrained model can achieve up to 11% absolute improvement (83% relative) over training from scratch and outperforms training from scratch in 30/36 of our comparisons. This transferability significantly reduces the reliance on manually annotated data for semantic occupancy forecasting: our method exceeds previous baselines with only 5% of the labeled training data of prior work. We also observed inefficiencies of current generative-model-based LiDAR world models, mainly through their under-compression of LiDAR data and inefficient training objectives. To address these issues, we propose a latent conditional flow matching (CFM)-based framework that achieves state-of-the-art reconstruction accuracy using only half the training data and a compression ratio 6 times higher than that of prior methods. Our model also achieves SOTA performance on semantic occupancy forecasting while being 1.98x-23x more computationally efficient (a 1.1x-3.9x FPS speedup) than previous methods.
@article{liu2025foundationallidarworldmodels,
title={Towards foundational LiDAR world models with efficient latent flow matching},
author={Tianran Liu and Shengwen Zhao and Nicholas Rhinehart},
year={2025},
eprint={2506.23434},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2506.23434},
}
CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting.
European Conference on Computer Vision, (ECCV), 2024.
European Conference on Computer Vision, (ECCV), 2024.
We propose CARFF, a method for predicting future 3D scenes given past observations. Our method maps 2D ego-centric images to a distribution over plausible 3D latent scene configurations and predicts the evolution of hypothesized scenes through time. Our latents condition a global Neural Radiance Field (NeRF) to represent a 3D scene model, enabling explainable predictions and straightforward downstream planning. This approach models the world as a POMDP and considers complex scenarios of uncertainty in environmental states and dynamics. Specifically, we employ a two-stage training of Pose-Conditional-VAE and NeRF to learn 3D representations, and auto-regressively predict latent scene representations utilizing a mixture density network. We demonstrate the utility of our method in scenarios using the CARLA driving simulator, where CARFF enables efficient trajectory and contingency planning in complex multi-agent autonomous driving scenarios involving occlusions.
@article{yang2024carff,
author = {Yang, Jiezhi and Desai, Khushi and Packer, Charles and Bhatia, Harshil and Rhinehart, Nicholas and McAllister, Rowan and Gonzalez, Joseph},
journal = {arXiv preprint arXiv:2401.18075},
title = {CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting},
year = {2024}
}
Is anyone there? learning a planner contingent on perceptual uncertainty.
Conference on Robot Learning, (CoRL), 2023.
Conference on Robot Learning, (CoRL), 2023.
Robots in complex multi-agent environments should reason about the intentions of observed and currently unobserved agents. In this paper, we present a new learning-based method for prediction and planning in complex multi-agent environments where the states of the other agents are partially-observed. Our approach, Active Visual Planning (AVP), uses high-dimensional observations to learn a flow-based generative model of multi-agent joint trajectories, including unobserved agents that may be revealed in the near future, depending on the robot’s actions. Our predictive model is implemented using deep neural networks that map raw observations to future detection and pose trajectories and is learned entirely offline using a dataset of recorded observations (not ground-truth states). Once learned, our predictive model can be used for contingency planning over the potential existence, intentions, and positions of unobserved agents. We demonstrate the effectiveness of AVP on a set of autonomous driving environments inspired by real-world scenarios that require reasoning about the existence of other unobserved agents for safe and efficient driving. In these environments, AVP achieves optimal closed-loop performance, while methods that do not reason about potential unobserved agents exhibit either overconfident or underconfident behavior.
@inproceedings{packer2023anyone,
author = {Packer, Charles and Rhinehart, Nicholas and McAllister, Rowan Thomas and Wright, Matthew A and Wang, Xin and He, Jeff and Levine, Sergey and Gonzalez, Joseph E},
booktitle = {Conference on Robot Learning},
organization = {PMLR},
pages = {1607--1617},
title = {Is anyone there? learning a planner contingent on perceptual uncertainty},
year = {2023}
}
S2Net: Stochastic Sequential Pointcloud Forecasting.
European Conference on Computer Vision, (ECCV), 2022.
European Conference on Computer Vision, (ECCV), 2022.
Predicting futures of surrounding agents is critical for autonomous systems such as self-driving cars. Instead of requiring accurate detection and tracking prior to trajectory prediction, an object agnostic Sequential Pointcloud Forecasting (SPF) task was proposed [28], which enables a forecast-then-detect pipeline effective for downstream detection and trajectory prediction. One limitation of prior work is that it forecasts only a deterministic sequence of future point clouds, despite the inherent uncertainty of dynamic scenes. In this work, we tackle the stochastic SPF problem by proposing a generative model with two main components: (1) a conditional variational recurrent neural network that models a temporally-dependent latent space; (2) a pyramid-LSTM that increases the fidelity of predictions with temporally-aligned skip connections. Through experiments on real-world autonomous driving datasets, our stochastic SPF model produces higher-fidelity predictions, reducing Chamfer distances by up to 56.6% compared to its deterministic counterpart. In addition, our model can estimate the uncertainty of predicted points, which can be helpful to downstream tasks.
@inproceedings{weng2022s2net,
author = {Weng, Xinshuo and Nan, Junyu and Lee, Kuan-Hui and McAllister, Rowan and Gaidon, Adrien and Rhinehart, Nicholas and Kitani, Kris},
booktitle = {European Conference on Computer Vision (ECCV)},
title = {S2Net: Stochastic Sequential Pointcloud Forecasting},
year = {2022}
}
Traffic prediction with reparameterized pushforward policy for autonomous vehicles.
U.S. Patent No. 11,189,171, 2021.
U.S. Patent No. 11,189,171, 2021.
Systems and methods for vehicle behavior prediction include an imaging device that captures images of a vehicle in traffic. A processing device including policy stored in a memory of the processing device in communication with the imaging device stochastically models future behavior of the vehicle based on the captured images. A policy simulator in communication with the processing device simulates the policy as a reparameterized pushforward policy of a base distribution. An evaluator receives the simulated policy from the policy simulator and performs cross-entropy optimization on the future behavior of the vehicle by analyzing the simulated policy and updating the policy according to cross-entropy error. An alert system retrieves the future behavior of the vehicle and recognizes hazardous trajectories of the future trajectories and generates an audible alert using a speaker.
@misc{vernaza2021traffic,
author = {Vernaza, Paul and Rhinehart, Nicholas},
month = {November~30},
note = {US Patent 11,189,171},
title = {Traffic prediction with reparameterized pushforward policy for autonomous vehicles},
year = {2021}
}
Inverting the pose forecasting pipeline with SPF2: Sequential pointcloud forecasting for sequential pose forecasting.
Conference on robot learning, (CoRL), 2021.
Conference on robot learning, (CoRL), 2021.
Many autonomous systems forecast aspects of the future in order to aid decision-making. For example, self-driving vehicles and robotic manipulation systems often forecast future object poses by first detecting and tracking objects. However, this detect-then-forecast pipeline is expensive to scale, as pose forecasting algorithms typically require labeled sequences of object poses, which are costly to obtain in 3D space. Can we scale performance without requiring additional labels? We hypothesize yes, and propose inverting the detect-then-forecast pipeline. Instead of detecting, tracking and then forecasting the objects, we propose to first forecast 3D sensor data (e.g., point clouds with $100$k points) and then detect/track objects on the predicted point cloud sequences to obtain future poses, i.e., a forecast-then-detect pipeline. This inversion makes it less expensive to scale pose forecasting, as the sensor data forecasting task requires no labels. Part of this work’s focus is on the challenging first step –Sequential Pointcloud Forecasting (SPF), for which we also propose an effective approach, SPFNet. To compare our forecast-then-detect pipeline relative to the detect-then-forecast pipeline, we propose an evaluation procedure and two metrics. Through experiments on a robotic manipulation dataset and two driving datasets, we show that SPFNet is effective for the SPF task, our forecast-then-detect pipeline outperforms the detect-then-forecast approaches to which we compared, and that pose forecasting performance improves with the addition of unlabeled data.
@inproceedings{weng2021inverting,
author = {Weng, Xinshuo and Wang, Jianren and Levine, Sergey and Kitani, Kris and Rhinehart, Nicholas},
booktitle = {Conference on robot learning},
organization = {PMLR},
pages = {11--20},
title = {Inverting the pose forecasting pipeline with SPF2: Sequential pointcloud forecasting for sequential pose forecasting},
year = {2021}
}
Information is power: Intrinsic control via information capture.
Advances in Neural Information Processing Systems, (NeurIPS), 2021.
Advances in Neural Information Processing Systems, (NeurIPS), 2021.
Humans and animals explore their environment and acquire useful skills even in the absence of clear goals, exhibiting intrinsic motivation. The study of intrinsic motivation in artificial agents is concerned with the following question: what is a good general-purpose objective for an agent? We study this question in dynamic partially-observed environments, and argue that a compact and general learning objective is to minimize the entropy of the agent’s state visitation estimated using a latent state-space model. This objective induces an agent to both gather information about its environment, corresponding to reducing uncertainty, and to gain control over its environment, corresponding to reducing the unpredictability of future world states. We instantiate this approach as a deep reinforcement learning agent equipped with a deep variational Bayes filter. We find that our agent learns to discover, represent, and exercise control of dynamic objects in a variety of partially-observed environments sensed with visual observations without extrinsic reward.
@article{rhinehart2021information,
author = {Rhinehart, Nicholas and Wang, Jenny and Berseth, Glen and Co-Reyes, John and Hafner, Danijar and Finn, Chelsea and Levine, Sergey},
journal = {Advances in Neural Information Processing Systems},
pages = {10745--10758},
title = {Information is power: Intrinsic control via information capture},
volume = {34},
year = {2021}
}
Generative adversarial inverse trajectory optimization for probabilistic vehicle forecasting.
U.S. Patent 10,739,773, 2020.
U.S. Patent 10,739,773, 2020.
Systems and methods for predicting vehicle behavior includes capturing images of a vehicle in traffic using an imaging device. Future behavior of the vehicle is stochastically modeled using a processing device including an energy-based model stored in a memory of the processing device. The energy-based model includes generating a distribution of possible future trajectories of the vehicle using a generator, sampling the distribution of possible future trajectories according to an energy value of each trajectory in the distribution of possible future trajectories an energy model to determine probable future trajectories, and optimizing parameters of each of the generator and the energy model using an optimizer. A user is audibly alerted with a speaker upon an alert system recognizing hazardous trajectories of the probable future trajectories.
@misc{vernaza2020generative,
author = {Vernaza, Paul and Choi, Wongun and Rhinehart, Nicholas},
month = {July~7},
note = {US Patent 10,705,531},
title = {Generative adversarial inverse trajectory optimization for probabilistic vehicle forecasting},
year = {2020}
}
Parrot: Data-driven behavioral priors for reinforcement learning.
International Conference on Learning Representations, (ICLR), 2020.
International Conference on Learning Representations, (ICLR), 2020.
Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an agent needs to learn. In other machine learning fields, such as natural language processing or computer vision, pre-training on large, previously collected datasets to bootstrap learning for new tasks has emerged as a powerful paradigm to reduce data requirements when learning a new task. In this paper, we ask the following question: how can we enable similarly useful pre-training for RL agents? We propose a method for pre-training behavioral priors that can capture complex input-output relationships observed in successful trials from a wide range of previously seen tasks, and we show how this learned prior can be used for rapidly learning new tasks without impeding the RL agent’s ability to try out novel behaviors. We demonstrate the effectiveness of our approach in challenging robotic manipulation domains involving image observations and sparse reward functions, where our method outperforms prior works by a substantial margin.
@article{singh2020parrot,
author = {Singh, Avi and Liu, Huihan and Zhou, Gaoyue and Yu, Albert and Rhinehart, Nicholas and Levine, Sergey},
journal = {arXiv preprint arXiv:2011.10024},
title = {Parrot: Data-driven behavioral priors for reinforcement learning},
year = {2020}
}
Deep Imitative Models for Flexible Inference, Planning, and Control.
International Conference on Learning Representations, (ICLR), 2020.
International Conference on Learning Representations, (ICLR), 2020.
Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based algorithms use dynamics models and reward functions to achieve goals. Yet, reward functions that evoke desirable behavior are often difficult to specify. In this paper, we propose Imitative Models to combine the benefits of IL and goal-directed planning. Imitative Models are probabilistic predictive models of desirable behavior able to plan interpretable expert-like trajectories to achieve specified goals. We derive families of flexible goal objectives, including constrained goal regions, unconstrained goal sets, and energy-based goals. We show that our method can use these objectives to successfully direct behavior. Our method substantially outperforms six IL approaches and a planning-based approach in a dynamic simulated autonomous driving task, and is efficiently learned from expert demonstrations without online data collection. We also show our approach is robust to poorly specified goals, such as goals on the wrong side of the road.
@inproceedings{rhinehart2020deep,
author = {Rhinehart, Nicholas and McAllister, Rowan and Levine, Sergey},
booktitle = {International Conference on Learning Representations (ICLR)},
title = {Deep Imitative Models for Flexible Inference, Planning, and Control},
year = {2020}
}
PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings.
Proceedings of the IEEE International Conference on Computer Vision, (ICCV), 2019.
Best Paper Award @ ICML 2019 Workshop on AI for Autonomous Driving
Proceedings of the IEEE International Conference on Computer Vision, (ICCV), 2019.
Best Paper Award @ ICML 2019 Workshop on AI for Autonomous Driving
For autonomous vehicles (AVs) to behave appropriately on roads populated by human-driven vehicles, they must be able to reason about the uncertain intentions and decisions of other drivers from rich perceptual information. Towards these capabilities, we present a probabilistic forecasting model of future interactions between a variable number of agents. We perform both standard forecasting and the novel task of conditional forecasting, which reasons about how all agents will likely respond to the goal of a controlled agent (here, the AV). We train models on real and simulated data to forecast vehicle trajectories given past positions and LIDAR. Our evaluation shows that our model is substantially more accurate in multi-agent driving scenarios compared to existing state-of-the-art. Beyond its general ability to perform conditional forecasting queries, we show that our model’s predictions of all agents improve when conditioned on knowledge of the AV’s goal, further illustrating its capability to model agent interactions.
@inproceedings{rhinehart2019precog,
author = {Rhinehart, Nicholas and McAllister, Rowan and Kitani, Kris and Levine, Sergey},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision},
title = {PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings},
year = {2019}
}
Jointly Forecasting and Controlling Behavior by Learning from High-Dimensional Data.
2019.
2019.
Achieving a precise predictive understanding of the future is difficult, yet widely studied in the natural sciences. Significant research activity has been dedicated to building testable models of cause and effect. From a certain view, the ability to forecast the universe is the “holy grail”; the ultimate goal of science. If we had it, we could anticipate, and therefore (at least implicitly) understand all observable phenomena. The human capability to forecast offers complementary motivation. Critical to our intelligence is our ability to plan behaviors by considering how our actions are likely to result in future payoff, especially in the presence of other collaborative and competitive agents. In this work, we seek to computationally model the future in the presence of agent behavior given rich observations of the environment. The brunt of our focus is to reason about what agents could do, instead of other sources of stochasticity. This focus on future agent behavior allows us to tightly couple and jointly perform forecasting and control. The field of Computer Vision (CV) is focused on designing algorithms to automatically understand images, videos, and other perceptual data. However, the field’s effort to-date focuses on non-interactive, present-focused tasks [79, 81, 158, 184]. Most CV contributions are algorithms to answer questions like “what is that”, and “what happened”, rather than “what could happen”, or “how could I achieve X”. Computer Vision has under-explored reasoning about the interactive and decision-based nature of the world. In contrast, Reinforcement Learning (RL) prioritizes modeling interactions and decisions by focusing on how to design algorithms to evoke behavior that maximizes a scalar reward signal. The resulting learning agents, in order to perform well, must have an understanding of how their current behaviors will affect their prospects of future reward. However, in the dominant paradigm of model-free RL [218], agents reason implicitly about the future. In contrast, model-based RL learns one-step dynamics to estimate “what could happen in the near future”. Yet model-based RL primarily focuses on control, rather than explicitly forecasting a single agent (let alone multiple agents). In this thesis, we consider the problem of designing algorithms to enable computational systems to (1) forecast future behavior of intelligent agents given rich observations of their environments, as well as to (2) use this reasoning for control. We believe these two problems should be tightly integrated and jointly considered, and use them to structure this thesis. We define forecasting to be the problem of estimating the set of possible outcomes of a system, whereas control is the problem of producing actions that generate a single outcome of a system. We often use Imitation Learning and Reinforcement Learning to formulate and situate our work. We contribute forecasting and control approaches to excel in diverse, realistic, single-agent, and multi-agent domains. The first part of the thesis focuses on progressively designing more capable forecasting models. We proceed through approaches to (1) forecast single actions of daily behavior by developing matrix factorization models [169], (2) forecast goal-driven action trajectories of daily behavior by developing Online Inverse Reinforcement Learning models [168, 170], (3) forecast motion trajectories of vehicles by developing a deep reversible generative models [171, 174]. The second part of the thesis focuses on progressively designing more capable models that tightly couple forecasting and control. We discuss (4) forecasting as auxiliary supervision for implicitly-planned control [228], (5) forecasting and explicitly planning with the same model [176], and (6) forecasting and planning future interactions of multiple agents [175].
@phdthesis{rhinehart2019jointly,
author = {Rhinehart, Nicholas},
school = {Carnegie Mellon University},
title = {Jointly Forecasting and Controlling Behavior by Learning from High-Dimensional Data},
year = {2019}
}
Generative Hybrid Representations for Activity Forecasting with No-Regret Learning.
Conference on Computer Vision and Pattern Recognition, (CVPR), 2019.
Conference on Computer Vision and Pattern Recognition, (CVPR), 2019.
Automatically reasoning about future human behaviors is a difficult problem but has significant practical applications to assistive systems. Part of this difficulty stems from learning systems’ inability to represent all kinds of behaviors. Some behaviors, such as motion, are best described with continuous representations, whereas others, such as picking up a cup, are best described with discrete representations. Furthermore, human behavior is generally not fixed: people can change their habits and routines. This suggests these systems must be able to learn and adapt continuously. In this work, we develop an efficient deep generative model to jointly forecast a person’s future discrete actions and continuous motions. On a large-scale egocentric dataset, EPIC-KITCHENS, we observe our method generates high-quality and diverse samples while exhibiting better generalization than related generative models. Finally, we propose a variant to continually learn our model from streaming data, observe its practical effectiveness, and theoretically justify its learning efficiency.
@article{guan2019generative,
author = {Guan, Jiaqi and Yuan, Ye and Kitani, Kris M and Rhinehart, Nicholas},
journal = {arXiv preprint arXiv:1904.06250},
title = {Generative Hybrid Representations for Activity Forecasting with No-Regret Learning},
year = {2019}
}
R2P2: A Reparameterized Pushforward Policy for Diverse, Precise Generative Path Forecasting.
Proceedings of the European Conference on Computer Vision, (ECCV), 2018.
Proceedings of the European Conference on Computer Vision, (ECCV), 2018.
We propose a method to forecast a vehicle’s ego-motion as a distribution over spatiotemporal paths, conditioned on features (e.g., from LIDAR and images) embedded in an overhead map. The method learns a policy inducing a distribution over simulated trajectories that is both “diverse” (produces most of the likely paths) and “precise” (mostly produces likely paths). This balance is achieved through minimization of a symmetrized cross-entropy between the distribution and demonstration data. By viewing the simulated-outcome distribution as the pushforward of a simple distribution under a simulation operator, we obtain expressions for the cross-entropy metrics that can be efficiently evaluated and differentiated, enabling stochastic-gradient optimization. We propose concrete policy architectures for this model, discuss our evaluation metrics relative to previously-used degenerate metrics, and demonstrate the superiority of our method relative to state-of-the-art methods in both the Kitti dataset and a similar but novel and larger real-world dataset explicitly designed for the vehicle forecasting domain.
@inproceedings{rhinehart2018r2p2,
author = {Rhinehart, Nicholas and Kitani, Kris M. and Vernaza, Paul},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
pages = {772--788},
title = {R2P2: A Reparameterized Pushforward Policy for Diverse, Precise Generative Path Forecasting},
year = {2018}
}