Camera rotation estimation from a single image is a challenging task, often requiring depth data and/or camera intrinsics, which are generally not available for in-the-wild videos. Although external sensors such as inertial measurement units (IMUs) can help, they often suffer from drift and are not applicable in non-inertial reference frames. We present U-ARE-ME, an algorithm that estimates camera rotation along with uncertainty from uncalibrated RGB images. Using a Manhattan World assumption, our method leverages the per-pixel geometric priors encoded in single-image surface normal predictions and performs optimisation over the SO(3) manifold. Given a sequence of images, we can use the per-frame rotation estimates and their uncertainty to perform multi-frame optimisation, achieving robustness and temporal consistency. Our experiments demonstrate that U-ARE-ME performs comparably to RGB-D methods and is more robust than sparse feature-based SLAM methods. We encourage the reader to view the accompanying video at this https URL for a visual overview of our method.
A Distributed Multi-Robot Framework for Exploration, Information Acquisition and Consensus (ICRA 2024)
The distributed coordination of robot teams performing complex tasks is challenging to formulate. The different aspects of a complete task such as local planning for obstacle avoidance, global goal coordination and collaborative mapping are often solved separately, when clearly each of these should influence the others for the most efficient behaviour. In this paper we use the example application of distributed information acquisition as a robot team explores a large space to show that we can formulate the whole problem as a single factor graph with multiple connected layers representing each aspect. We use Gaussian Belief Propagation (GBP) as the inference mechanism, which permits parallel, on-demand or asynchronous computation for efficiency when different aspects are more or less important. This is the first time that a distributed GBP multi-robot solver has been proven to enable intelligent collaborative behaviour rather than just guiding robots to individual, selfish goals.
2023
Distributing Collaborative Multi-Robot Planning With Gaussian Belief Propagation
Aalok Patwardhan, Riku Murai, and Andrew J. Davison
Precise coordinated planning over a forward time window enables safe and highly efficient motion when many robots must work together in tight spaces, but this would normally require centralised control of all devices which is difficult to scale. We demonstrate GBP Planning, a new purely distributed technique based on Gaussian Belief Propagation for multi-robot planning problems, formulated by a generic factor graph defining dynamics and collision constraints over a forward time window. In simulations, we show that our method allows high performance collaborative planning where robots are able to cross each other in busy, intricate scenarios. They maintain shorter, quicker and smoother trajectories than alternative distributed planning techniques even in cases of communication failure. We encourage the reader to view the accompanying video demonstration.
Distributed Formation Planning for Robot Swarms
Aalok Patwardhan
In Workshop on Distributed Graph Algorithms for Robotics at ICRA, 2023
A swarm of robots is often required to create formations in space whilst avoiding obstacles in the environment. In order to do so a high degree of coordination is required between the robots to ensure smooth and safe paths. We formulate formation planning as performing inference on a factor graph using Gaussian Belief Propagation (GBP). This work is an outline of the real time and interactive demos we would like to show at the Distributed Graphs Workshop at ICRA 2023. We show some examples of the demos that will be displayed, and hope that this work encourages more research in this field.
Distributed Formation Planning for Robot SwarmsIn Workshop on Distributed Graph Algorithms for Robotics at ICRA, 2023
