Related papers: BEINGS: Bayesian Embodied Image-goal Navigation wi…
Dynamic scene rendering opens new avenues in autonomous driving by enabling closed-loop simulations with photorealistic data, which is crucial for validating end-to-end algorithms. However, the complex and highly dynamic nature of traffic…
The rapid growth of 3D Gaussian Splatting (3DGS) has revolutionized neural rendering, enabling real-time production of high-quality renderings. However, the previous 3DGS-based methods have limitations in urban scenes due to reliance on…
This paper presents an architecture and methodology to empower a service robot to navigate an indoor environment with semantic decision making, given RGB ego view. This method leverages the knowledge of robot's actuation capability and that…
Effective embodied exploration requires agents to accumulate and retain spatial knowledge over time. However, existing scene representations, such as discrete scene graphs or static view-based snapshots, lack \textit{post-hoc…
We propose a vision-based method that localizes a ground vehicle using publicly available satellite imagery as the only prior knowledge of the environment. Our approach takes as input a sequence of ground-level images acquired by the…
3D Gaussian Splatting (3DGS) allows flexible adjustments to scene representation, enabling continuous optimization of scene quality during dense visual simultaneous localization and mapping (SLAM) in static environments. However, 3DGS faces…
Today's state of the art visual navigation agents typically consist of large deep learning models trained end to end. Such models offer little to no interpretability about the learned skills or the actions of the agent taken in response to…
Most Gaussian Splatting techniques that provide a 3D semantic representation of the scene do not optimize the underlying 3D geometry, making object-level editing or asset extraction challenging. Recent methods, such as COBGS, Trace3D,…
Object Goal Navigation (ObjectNav) task is to navigate an agent to an object category in unseen environments without a pre-built map. In this paper, we solve this task by predicting the distance to the target using semantically-related…
While neural rendering has demonstrated impressive capabilities in 3D scene reconstruction and novel view synthesis, it heavily relies on high-quality sharp images and accurate camera poses. Numerous approaches have been proposed to train…
Images are a convenient way to specify which particular object instance an embodied agent should navigate to. Solving this task requires semantic visual reasoning and exploration of unknown environments. We present a system that can perform…
In cluttered scenes with inevitable occlusions and incomplete observations, selecting informative viewpoints is essential for building a reliable representation. In this context, 3D Gaussian Splatting (3DGS) offers a distinct advantage, as…
We propose improving the cross-target and cross-scene generalization of visual navigation through learning an agent that is guided by conceiving the next observations it expects to see. This is achieved by learning a variational Bayesian…
Emerging 3D scene representations, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have demonstrated their effectiveness in Simultaneous Localization and Mapping (SLAM) for photo-realistic rendering, particularly…
We present Nav2Goal, a data-efficient and end-to-end learning method for goal-conditioned visual navigation. Our technique is used to train a navigation policy that enables a robot to navigate close to sparse geographic waypoints provided…
Visual servoing, the method of controlling robot motion through feedback from visual sensors, has seen significant advancements with the integration of optical flow-based methods. However, its application remains limited by inherent…
Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject…
Recent trends in SLAM and visual navigation have embraced 3D Gaussians as the preferred scene representation, highlighting the importance of estimating camera poses from a single image using a pre-built Gaussian model. However, existing…
To achieve autonomy in unknown and unstructured environments, we propose a method for semantic-based planning under perceptual uncertainty. This capability is crucial for safe and efficient robot navigation in environment with…
Non-invasive electroencephalography (EEG)-based brain-computer interfaces (BCIs) offer an intuitive means for individuals with severe motor impairments to independently operate assistive robotic wheelchairs and navigate built environments.…