116 citations · 458 across the 20 of their papers we have counts for
21 papers
CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting
Jiezhi Yang, Khushi Desai, Charles Packer +4
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 configura…
Offline Reinforcement Learning for Visual Navigation
Dhruv Shah, Arjun Bhorkar, Hrish Leen +3
Reinforcement learning can enable robots to navigate to distant goals while optimizing user-specified reward functions, including preferences for following lanes, staying on paved…
Hybrid Imitative Planning with Geometric and Predictive Costs in Off-road Environments
Nitish Dashora, Daniel Shin, Dhruv Shah +5
Geometric methods for solving open-world off-road navigation tasks, by learning occupancy and metric maps, provide good generalization but can be brittle in outdoor environments th…
Explore and Control with Adversarial Surprise
Arnaud Fickinger, Natasha Jaques, Samyak Parajuli +5
Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering. However, a central challen…
Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models
Nicholas Rhinehart, Jeff He, Charles Packer +4
Humans have a remarkable ability to make decisions by accurately reasoning about future events, including the future behaviors and states of mind of other agents. Consider driving…
Rapid Exploration for Open-World Navigation with Latent Goal Models
Dhruv Shah, Benjamin Eysenbach, Gregory Kahn +2
We describe a robotic learning system for autonomous exploration and navigation in diverse, open-world environments. At the core of our method is a learned latent variable model of…
ViNG: Learning Open-World Navigation with Visual Goals
Dhruv Shah, Benjamin Eysenbach, Gregory Kahn +2
We propose a learning-based navigation system for reaching visually indicated goals and demonstrate this system on a real mobile robot platform. Learning provides an appealing alte…
Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
Avi Singh, Huihan Liu, Gaoyue Zhou +3
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.…
Conservative Safety Critics for Exploration
Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart +3
Safe exploration presents a major challenge in reinforcement learning (RL): when active data collection requires deploying partially trained policies, we must ensure that these pol…
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
Angelos Filos, Panagiotis Tigas, Rowan McAllister +3
Out-of-training-distribution (OOD) scenarios are a common challenge of learning agents at deployment, typically leading to arbitrary deductions and poorly-informed decisions. In pr…
Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecasting
Xinshuo Weng, Jianren Wang, Sergey Levine +2
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 ob…
PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings
Nicholas Rhinehart, Rowan McAllister, Kris Kitani +1
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…
Generative Hybrid Representations for Activity Forecasting with No-Regret Learning
Jiaqi Guan, Ye Yuan, Kris M. Kitani +1
Automatically reasoning about future human behaviors is a difficult problem but has significant practical applications to assistive systems. Part of this difficulty stems from lear…
Deep Imitative Models for Flexible Inference, Planning, and Control
Nicholas Rhinehart, Rowan McAllister, Sergey Levine
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…
Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information
Arjun Sharma, Mohit Sharma, Nicholas Rhinehart +1
The use of imitation learning to learn a single policy for a complex task that has multiple modes or hierarchical structure can be challenging. In fact, previous work has shown tha…
Learning Neural Parsers with Deterministic Differentiable Imitation Learning
Tanmay Shankar, Nicholas Rhinehart, Katharina Muelling +1
We explore the problem of learning to decompose spatial tasks into segments, as exemplified by the problem of a painting robot covering a large object. Inspired by the ability of c…
Predictive-State Decoders: Encoding the Future into Recurrent Networks
Arun Venkatraman, Nicholas Rhinehart, Wen Sun +5
Recurrent neural networks (RNNs) are a vital modeling technique that rely on internal states learned indirectly by optimization of a supervised, unsupervised, or reinforcement trai…
N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning
Anubhav Ashok, Nicholas Rhinehart, Fares Beainy +1
While bigger and deeper neural network architectures continue to advance the state-of-the-art for many computer vision tasks, real-world adoption of these networks is impeded by ha…
First-Person Activity Forecasting with Online Inverse Reinforcement Learning
Nicholas Rhinehart, Kris M. Kitani
We address the problem of incrementally modeling and forecasting long-term goals of a first-person camera wearer: what the user will do, where they will go, and what goal they seek…
Learning Action Maps of Large Environments via First-Person Vision
Nicholas Rhinehart, Kris M. Kitani
When people observe and interact with physical spaces, they are able to associate functionality to regions in the environment. Our goal is to automate dense functional understandin…
Visual Chunking: A List Prediction Framework for Region-Based Object Detection
Nicholas Rhinehart, Jiaji Zhou, Martial Hebert +1
We consider detecting objects in an image by iteratively selecting from a set of arbitrarily shaped candidate regions. Our generic approach, which we term visual chunking, reasons…