Search Results for author:
Found 35 papers, 13 papers with code
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2).
Ranked #4 on
3D Reconstruction
on Data3D−R2N2
Model-Driven Feed-Forward Prediction for Manipulation of Deformable Objects
A fully featured 3D model of the garment is constructed in real-time and volumetric features are then used to obtain the most similar model in the database to predict the object category and pose.
Scene Graph Generation by Iterative Message Passing
In this work, we explicitly model the objects and their relationships using scene graphs, a visually-grounded graphical structure of an image.
Ranked #9 on
Panoptic Scene Graph Generation
on PSG Dataset
Neural Task Programming: Learning to Generalize Across Hierarchical Tasks
In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction.
PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
We present PointFusion, a generic 3D object detection method that leverages both image and 3D point cloud information.
Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
We hypothesize that to successfully generalize to unseen complex tasks from a single video demonstration, it is necessary to explicitly incorporate the compositional structure of the tasks into the model.
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
A key technical challenge in performing 6D object pose estimation from RGB-D image is to fully leverage the two complementary data sources.
Ranked #4 on
6D Pose Estimation
on LineMOD
Procedure Planning in Instructional Videos
In this paper, we study the problem of procedure planning in instructional videos, which can be seen as a step towards enabling autonomous agents to plan for complex tasks in everyday settings such as cooking.
Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
The key technical challenge is that the symbol grounding is prone to error with limited training data and leads to subsequent symbolic planning failures.
Situational Fusion of Visual Representation for Visual Navigation
A complex visual navigation task puts an agent in different situations which call for a diverse range of visual perception abilities.
Regression Planning Networks
Recent learning-to-plan methods have shown promising results on planning directly from observation space.
6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
We present 6-PACK, a deep learning approach to category-level 6D object pose tracking on RGB-D data.
Ranked #1 on
6D Pose Estimation using RGBD
on REAL275
(Rerr metric)
Positive-Unlabeled Reward Learning
Learning reward functions from data is a promising path towards achieving scalable Reinforcement Learning (RL) for robotics.
Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
In the second stage of GTI, we collect a small set of rollouts from the unconditioned stochastic policy of the first stage, and train a goal-directed agent to generalize to novel start and goal configurations.
Human-in-the-Loop Imitation Learning using Remote Teleoperation
We develop a simple and effective algorithm to train the policy iteratively on new data collected by the system that encourages the policy to learn how to traverse bottlenecks through the interventions.
Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control
Key to such capability is hand-eye coordination, a cognitive ability that enables humans to adaptively direct their movements at task-relevant objects and be invariant to the objects' absolute spatial location.
What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
Based on the study, we derive a series of lessons including the sensitivity to different algorithmic design choices, the dependence on the quality of the demonstrations, and the variability based on the stopping criteria due to the different objectives in training and evaluation.
Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration
Our method co-optimizes a human policy and a robot policy in an interactive learning process: the human policy learns to generate diverse and plausible collaborative behaviors from demonstrations while the robot policy learns to assist by estimating the unobserved latent strategy of its human collaborator.
Robust Trajectory Prediction against Adversarial Attacks
We demonstrate that our method is able to improve the performance by 46% on adversarial data and at the cost of only 3% performance degradation on clean data, compared to the model trained with clean data.
BITS: Bi-level Imitation for Traffic Simulation
We empirically validate our method, named Bi-level Imitation for Traffic Simulation (BITS), with scenarios from two large-scale driving datasets and show that BITS achieves balanced traffic simulation performance in realism, diversity, and long-horizon stability.
AdvDO: Realistic Adversarial Attacks for Trajectory Prediction
Trajectory prediction is essential for autonomous vehicles (AVs) to plan correct and safe driving behaviors.
ProgPrompt: Generating Situated Robot Task Plans using Large Language Models
To ameliorate that effort, large language models (LLMs) can be used to score potential next actions during task planning, and even generate action sequences directly, given an instruction in natural language with no additional domain information.
LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation
We also show that the learned skills can be reused to accelerate learning in new tasks domains and transfer to a physical robot platform.
Guided Conditional Diffusion for Controllable Traffic Simulation
Controllable and realistic traffic simulation is critical for developing and verifying autonomous vehicles.
Foundation Models for Semantic Novelty in Reinforcement Learning
Effectively exploring the environment is a key challenge in reinforcement learning (RL).
Partial-View Object View Synthesis via Filtered Inversion
At inference, given one or more views of a novel real-world object, FINV first finds a set of latent codes for the object by inverting the generative model from multiple initial seeds.
Language-Guided Traffic Simulation via Scene-Level Diffusion
Realistic and controllable traffic simulation is a core capability that is necessary to accelerate autonomous vehicle (AV) development.
Evolutionary Curriculum Training for DRL-Based Navigation Systems
Additionally, an evolutionary training environment generates all the curriculum to improve the DRL model's inadequate skills tested in the previous evaluation.
Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning
Furthermore, the intrinsic heterogeneity in human behavior can produce equally successful but disparate demonstrations, further exacerbating the challenge of discerning demonstration quality.
Human-in-the-Loop Task and Motion Planning for Imitation Learning
Finally, we collected 2. 1K demos with HITL-TAMP across 12 contact-rich, long-horizon tasks and show that the system often produces near-perfect agents.
Neural Field Dynamics Model for Granular Object Piles Manipulation
We present a learning-based dynamics model for granular material manipulation.
NOD-TAMP: Multi-Step Manipulation Planning with Neural Object Descriptors
Developing intelligent robots for complex manipulation tasks in household and factory settings remains challenging due to long-horizon tasks, contact-rich manipulation, and the need to generalize across a wide variety of object shapes and scene layouts.
EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
We present EmerNeRF, a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes.
InstantSplat: Unbounded Sparse-view Pose-free Gaussian Splatting in 40 Seconds
This pre-processing is usually conducted via a Structure-from-Motion (SfM) pipeline, a procedure that can be slow and unreliable, particularly in sparse-view scenarios with insufficient matched features for accurate reconstruction.
A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches
Task and Motion Planning (TAMP) integrates high-level task planning and low-level motion planning to equip robots with the autonomy to effectively reason over long-horizon, dynamic tasks.
