A goal of multi-view clustering (MVC) is to discover common features of an object across views while identifying unique features within each view. Deep neural networks are good at feature learning on large-scale unlabeled datasets, but most deep MVC methods struggle to extract and utilize complementary information from view-unique features. Additionally, many lack support for single-sample inference, limiting applications. This paper presents a novel Common and Unique Representation Deep Embedded Clustering (CUR-DEC) architecture and optimization method that learns view-invariant representations, aiding in clustering assignments by leveraging view-unique information. This method is suitable for single-sample inference. We first pretrain an autoencoder to extract both view-common and view-unique features, then a common cluster representation is learned by leveraging complementary information. Experimental results on multi-view datasets show that our method provides significant improvements compared to other deep multi-view clustering methods.

This paper introduces a novel fan-out model that improves accuracy over previous models. The commonly used models rely on neglect time, the time an agent operates independently, which confounds both human and robot abilities. The proposed model separates neglect time into two functionally distinct concepts: the time a robot can operate self-sufficiently, and the time a human estimates the robot can do so. Previous research indicates fan-out is often overestimated. This work explains why robot ability provides an upper bound to fan-out, but that actual achieved fan-out is influenced by both the human and robot abilities. We conduct a study to validate this new model and show improved performance over the two most common fan-out models. The results show that both previous models overestimate as predicted. Using the new fan-out model, we show that as the difference between human estimation and robot abilities grows, the actual fan-out will fall further from the upper bound potential fan-out. By including assessments of both the robotic and human elements, the new model provides a more nuanced understanding of the dynamics at play and the factors involved in scaling Human Multi-Robot Teams.

Scalability of human multi-robot teams is quickly becoming a crucial area of research as autonomous systems become more capable and sophisticated. A key research challenge is developing predictive measures of scalability, such as fan-out. This paper presents the results from a study that confirms the improved accuracy of a novel fan-out model over two previous models. It utilizes a new test domain to assess scalability and investigate the role of uncertainty through a variety of complexities driven by environmental factors, robot behaviors, and human-robot interactions. Our analysis highlights potential enhancements to optimize model accuracy across all the models. Finally, we show that when calibrating for measurement error, the new model is bounded, which sets it apart from previous models that are unbounded. The new model provides a more nuanced understanding of the dynamics at play and the factors involved in scaling Human Multi-Robot Teams under uncertainty.

Humanoid robots possess the ability to perform complex tasks in challenging environments. However, they require a model of the surroundings in a representation that is sufficient enough for downstream tasks such as footstep planning. The maps generated by existing mapping algorithms are either sparse, insufficient for footstep planning, memory intensive, or too slow for dynamic humanoid behaviors. In this work, we develop a mapping algorithm that combines planar region measurements along with kinematic-inertial state estimates to build a dense but efficient map of bounded planar surfaces. We present novel algorithms for plane feature matching, tracking and registration for mapping within a factor graph framework. The generated map is not only memory efficient, but also offers higher reliability and speed in bipedal footstep planning, than was possible earlier. The complete algorithm is also demonstrated using a full-scale humanoid robot, Nadia, walking over both flat ground and rough terrain utilizing the generated terrain map.

For achieving significant levels of autonomy, legged robot behaviors require perceptual awareness of both the terrain for traversal, as well as structures and objects in their surroundings for planning, obstacle avoidance, and high-level decision making. In this work, we present a perception engine for legged robots that extracts the necessary information for developing semantic, contextual, and metric awareness of their surroundings. Our custom sensor configuration consists of (1) an active depth sensor, (2) two monocular cameras looking sideways, (3) a passive stereo sensor observing the terrain, (4) a forward facing active depth camera, and (5) a rotating 3D LIDAR with a large vertical field-of-view (FOV). The mutual overlap in the sensors' FOVs allows us to redundantly detect and track objects of both dynamic and static types. We fuse class masks generated by a semantic segmentation model with LIDAR and depth data to accurately identify and track individual instances of dynamically moving objects. In parallel, active depth and passive stereo streams of the terrain are also fused to map the terrain using the on-board GPU. We evaluate the engine using two different humanoid behaviors, (1) look-and-step and (2) track-and-follow, on the Boston Dynamics Atlas.

Legged robots require fast and accurate representation of their surrounding terrain to achieve behaviors such as running, push recovery, continuous walking, backflips, while also utilizing on-board computational resources efficiently. The desired tasks can be achieved efficiently by representing the environment using planar regions. However, existing methods for planar region extraction are either too slow or require significant compute time on the Central Processing Unit (CPU). In this work we exploit key properties of depth images and Graphical Processing Unit (GPU) to estimate planar regions around the robot at very high frame rates of 150-200 Hz. The proposed algorithm uses a set of fully customizable and interchangeable set of kernel layers on the GPU to process the depth map in parallel and generate a locally connected graph structure, which is later separated into planar components using a basic depth-first search. We test the proposed algorithm on the Atlas robot while performing different walking behaviors on oriented cinder blocks, as well as in simulation with simulated sensor and robot. The algorithm is open-sourced for research on legged robots and other fields.

This paper presents combined velocity-heading control of a planar snake robot for the autonomous navigation and obstacle avoidance in a simulation environment. The kinematics and dynamics of the snake robot were derived using the articulated-body algorithm without considering the non-holonomic constraints. A double-layer controller was designed to control both heading direction and average velocity through joint motion control. We adopted a rule-based expert system for autonomous navigation while avoiding obstacles/restricted-areas. The guidance commands were realized by two proportional controllers that use feedback of the estimated speed and heading of the robot. To validate the combined velocity-heading controller, a series of simulations were carried out for a snake robot with 6 links (8 DOF). The autonomous navigation and obstacle-avoidance algorithms provided the commands to follow the desired trajectories. The simulation results showed the effectiveness of the controller in following the desired heading directions and achieving targeted velocities with small errors to reach the goal position by avoiding obstacles.