Search Results for author:
Found 46 papers, 26 papers with code
Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
We aim to redefine robust ego-motion estimation and photorealistic 3D reconstruction by addressing a critical limitation: the reliance on noise-free data in existing models.
Robust Bayesian Scene Reconstruction by Leveraging Retrieval-Augmented Priors
However, this can be brittle to noisy real-world observations and objects not contained in the dataset, and cannot reason about their confidence.
SplaTraj: Camera Trajectory Generation with Semantic Gaussian Splatting
These regions are then projected to the camera's view as it moves over time and a cost is constructed.
PhotoReg: Photometrically Registering 3D Gaussian Splatting Models
Advances in photorealistic environment models have enabled robots to develop hyper-realistic reconstructions, which can be used to generate images that are intuitive for human inspection.
3D Foundation Models Enable Simultaneous Geometry and Pose Estimation of Grasped Objects
We empirically evaluate our approach on a robot manipulator holding a diverse set of real-world objects.
RecGS: Removing Water Caustic with Recurrent Gaussian Splatting
Water caustics are commonly observed in seafloor imaging data from shallow-water areas.
From Perfect to Noisy World Simulation: Customizable Embodied Multi-modal Perturbations for SLAM Robustness Benchmarking
Embodied agents require robust navigation systems to operate in unstructured environments, making the robustness of Simultaneous Localization and Mapping (SLAM) models critical to embodied agent autonomy.
Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception
Constructing large-scale labeled datasets for multi-modal perception model training in autonomous driving presents significant challenges.
Unifying Scene Representation and Hand-Eye Calibration with 3D Foundation Models
We demonstrate that JCR can build effective scene representations using a low-cost RGB camera attached to a manipulator, without prior calibration.
DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark
Humans have the remarkable ability to construct consistent mental models of an environment, even under limited or varying levels of illumination.
Customizable Perturbation Synthesis for Robust SLAM Benchmarking
To this end, we propose a novel, customizable pipeline for noisy data synthesis, aimed at assessing the resilience of multi-modal SLAM models against various perturbations.
Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis
Motivated by the impressive open-set performance and content generation capabilities of web-scale, large-capacity pre-trained models (i. e., foundation models) in research fields such as Natural Language Processing (NLP) and Computer Vision (CV), we devote this survey to exploring (i) how these existing foundation models from NLP and CV can be applied to the field of general-purpose robotics, and also exploring (ii) what a robotics-specific foundation model would look like.
Learning Orbitally Stable Systems for Diagrammatically Teaching
In this work, we tackle the problem of teaching a robot to approach a surface and then follow cyclic motion on it, where the cycle of the motion can be arbitrarily specified by a single user-provided sketch over an image from the robot's camera.
Reasoning about the Unseen for Efficient Outdoor Object Navigation
We introduce a new task OUTDOOR, a new mechanism for Large Language Models (LLMs) to accurately hallucinate possible futures, and a new computationally aware success metric for pushing research forward in this more complex domain.
Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching
Diagrammatic Teaching aims to teach robots novel skills by prompting the user to sketch out demonstration trajectories on 2D images of the scene, these are then synthesised as a generative model of motion trajectories in 3D task space.
Hyperspherical Embedding for Point Cloud Completion
Most real-world 3D measurements from depth sensors are incomplete, and to address this issue the point cloud completion task aims to predict the complete shapes of objects from partial observations.
Beyond NeRF Underwater: Learning Neural Reflectance Fields for True Color Correction of Marine Imagery
The proposed technique integrates underwater light effects into a volume rendering framework with end-to-end differentiability.
LiSnowNet: Real-time Snow Removal for LiDAR Point Cloud
LiDARs have been widely adopted to modern self-driving vehicles, providing 3D information of the scene and surrounding objects.
CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations
Recent advances in neural radiance fields (NeRFs) achieve state-of-the-art novel view synthesis and facilitate dense estimation of scene properties.
Energy-optimal Three-dimensional Path-following Control of Autonomous Underwater Vehicles under Ocean Currents
In the first stage, the surge velocity, heave velocity, and pitch angle setpoints are optimized by minimizing the required vehicle propulsion energy under currents, and the line-of-sight (LOS) guidance law is used to generate the yaw angle setpoint that ensures path following.
Learning Cross-Scale Visual Representations for Real-Time Image Geo-Localization
Robot localization remains a challenging task in GPS denied environments.
Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks
Point cloud analysis is an area of increasing interest due to the development of 3D sensors that are able to rapidly measure the depth of scenes accurately.
BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation
BiTraP estimates the goal (end-point) of trajectories and introduces a novel bi-directional decoder to improve longer-term trajectory prediction accuracy.
Ranked #2 on
Trajectory Prediction
on JAAD
Point Set Voting for Partial Point Cloud Analysis
This paper illustrates that this proposed method achieves state-of-the-art performance on shape classification, part segmentation and point cloud completion.
Pixel-Wise Motion Deblurring of Thermal Videos
To address this problem, this paper formulates reversing the effect of thermal inertia at a single pixel as a Least Absolute Shrinkage and Selection Operator (LASSO) problem which we can solve rapidly using a quadratic programming solver.
Off The Beaten Sidewalk: Pedestrian Prediction In Shared Spaces For Autonomous Vehicles
Pedestrians and drivers interact closely in a wide range of environments.
Robotics
Parametric Design of Underwater Optical Systems
The design of optical systems for underwater vehicles is a complex process where the selection of cameras, lenses, housings, and operational parameters greatly influence the performance of the complete system.
SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images
There has been much recent interest in deep learning methods for monocular image based object pose estimation.
Reachable Sets for Safe, Real-Time Manipulator Trajectory Design
At runtime, in each receding-horizon planning iteration, ARMTD constructs a reachable set of the entire arm in workspace and intersects it with obstacles to generate sub-differentiable and provably-conservative collision-avoidance constraints on the trajectory parameters.
Robotics
Shadow Transfer: Single Image Relighting For Urban Road Scenes
There have been impressive advances in the realm of image to image translation in transferring previously unseen visual effects into a dataset, specifically in day to night translation.
On-Demand Trajectory Predictions for Interaction Aware Highway Driving
Highway driving places significant demands on human drivers and autonomous vehicles (AVs) alike due to high speeds and the complex interactions in dense traffic.
Robotics Signal Processing
LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery
An accurate depth map of the environment is critical to the safe operation of autonomous robots and vehicles.
Stochastic Sampling Simulation for Pedestrian Trajectory Prediction
Our work demonstrates the effectiveness and potential of using simulation as a substitution for human annotation efforts to train high-performing prediction algorithms such as the DNNs.
Robotics
Guaranteed Safe Reachability-based Trajectory Design for a High-Fidelity Model of an Autonomous Passenger Vehicle
Trajectory planning is challenging for autonomous cars since they operate in unpredictable environments with limited sensor horizons.
Systems and Control
Bridging the Gap Between Safety and Real-Time Performance in Receding-Horizon Trajectory Design for Mobile Robots
At runtime, the FRS is used to map obstacles to the space of parameterized trajectories, which allows RTD to select a safe trajectory at every planning iteration.
Robotics Systems and Control
SilhoNet: An RGB Method for 6D Object Pose Estimation
Autonomous robot manipulation involves estimating the translation and orientation of the object to be manipulated as a 6-degree-of-freedom (6D) pose.
Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for Sim-to-Real Domain Adaptation
This domain shift is especially exaggerated between synthetic and real datasets.
DispSegNet: Leveraging Semantics for End-to-End Learning of Disparity Estimation from Stereo Imagery
Initial disparity estimates are refined with an embedding learned from the semantic segmentation branch of the network.
Bio-LSTM: A Biomechanically Inspired Recurrent Neural Network for 3D Pedestrian Pose and Gait Prediction
In applications such as autonomous driving, it is important to understand, infer, and anticipate the intention and future behavior of pedestrians.
PedX: Benchmark Dataset for Metric 3D Pose Estimation of Pedestrians in Complex Urban Intersections
This paper presents a novel dataset titled PedX, a large-scale multimodal collection of pedestrians at complex urban intersections.
Modeling Camera Effects to Improve Visual Learning from Synthetic Data
Recent work has focused on generating synthetic imagery to increase the size and variability of training data for learning visual tasks in urban scenes.
Failing to Learn: Autonomously Identifying Perception Failures for Self-driving Cars
We show that a state-of-the-art detector, tracker, and our classifier trained only on synthetic data can identify valid errors on KITTI tracking dataset with an average precision of 0. 94.
Safe Trajectory Synthesis for Autonomous Driving in Unforeseen Environments
Path planning for autonomous vehicles in arbitrary environments requires a guarantee of safety, but this can be impractical to ensure in real-time when the vehicle is described with a high-fidelity model.
Systems and Control Robotics
WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images
Due to the depth-dependent water column effects inherent to underwater environments, we show that our end-to-end network implicitly learns a coarse depth estimate of the underwater scene from monocular underwater images.
Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?
Deep learning has rapidly transformed the state of the art algorithms used to address a variety of problems in computer vision and robotics.
