4D Panoptic Segmentation as Invariant and Equivariant Field Prediction

In this paper, we develop rotation-equivariant neural networks for 4D panoptic segmentation. 4D panoptic segmentation is a recently established benchmark task for autonomous driving, which requires recognizing semantic classes and object instances on the road based on LiDAR scans, as well as assigning temporally consistent IDs to instances across time. We observe that the driving scenario is symmetric to rotations on the ground plane. Therefore, rotation-equivariance could provide better generalization and more robust feature learning. Specifically, we review the object instance clustering strategies, and restate the centerness-based approach and the offset-based approach as the prediction of invariant scalar fields and equivariant vector fields. Other sub-tasks are also unified from this perspective, and different invariant and equivariant layers are designed to facilitate their predictions. Through evaluation on the standard 4D panoptic segmentation benchmark of SemanticKITTI, we show that our equivariant models achieve higher accuracy with lower computational costs compared to their non-equivariant counterparts. Moreover, our method sets the new state-of-the-art performance and achieves 1st place on the SemanticKITTI 4D Panoptic Segmentation leaderboard.

Hybrid Contact Preintegration for Visual-Inertial-Contact State Estimation Using Factor Graphs

The factor graph framework is a convenient modeling technique for robotic state estimation where states are represented as nodes, and measurements are modeled as factors. When designing a sensor fusion framework for legged robots, one often has access to visual, inertial, joint encoder, and contact sensors. While visual-inertial odometry has been studied extensively in this framework, the addition of a preintegrated contact factor for legged robots has been only recently proposed. This allowed for integration of encoder and contact measurements into existing factor graphs, however, new nodes had to be added to the graph every time contact was made or broken. In this work, to cope with the problem of switching contact frames, we propose a hybrid contact preintegration theory that allows contact information to be integrated through an arbitrary number of contact switches. The proposed hybrid modeling approach reduces the number of required variables in the nonlinear optimization problem by only requiring new states to be added alongside camera or selected keyframes. This method is evaluated using real experimental data collected from a Cassie-series robot where the trajectory of the robot produced by a motion capture system is used as a proxy for ground truth. The evaluation shows that inclusion of the proposed preintegrated hybrid contact factor alongside visual-inertial navigation systems improves estimation accuracy as well as robustness to vision failure, while its generalization makes it more accessible for legged platforms.

A Radio-Inertial Localization and Tracking System with BLE Beacons Prior Maps

In this paper, we develop a system for the low-cost indoor localization and tracking problem using radio signal strength indicator, Inertial Measurement Unit (IMU), and magnetometer sensors. We develop a novel and simplified probabilistic IMU motion model as the proposal distribution of the sequential Monte-Carlo technique to track the robot trajectory. Our algorithm can globally localize and track a robot with a priori unknown location, given an informative prior map of the Bluetooth Low Energy (BLE) beacons. Also, we formulate the problem as an optimization problem that serves as the Back-end of the algorithm mentioned above (Front-end). Thus, by simultaneously solving for the robot trajectory and the map of BLE beacons, we recover a continuous and smooth trajectory of the robot, corrected locations of the BLE beacons, and the time-varying IMU bias. The evaluations achieved using hardware show that through the proposed closed-loop system the localization performance can be improved; furthermore, the system becomes robust to the error in the map of beacons by feeding back the optimized map to the Front-end.

Contact-Aided Invariant Extended Kalman Filtering for Legged Robot State Estimation

This paper derives a contact-aided inertial navigation observer for a 3D bipedal robot using the theory of invariant observer design. Aided inertial navigation is fundamentally a nonlinear observer design problem; thus, current solutions are based on approximations of the system dynamics, such as an Extended Kalman Filter (EKF), which uses a system's Jacobian linearization along the current best estimate of its trajectory. On the basis of the theory of invariant observer design by Barrau and Bonnabel, and in particular, the Invariant EKF (InEKF), we show that the error dynamics of the point contact-inertial system follows a log-linear autonomous differential equation; hence, the observable state variables can be rendered convergent with a domain of attraction that is independent of the system's trajectory. Due to the log-linear form of the error dynamics, it is not necessary to perform a nonlinear observability analysis to show that when using an Inertial Measurement Unit (IMU) and contact sensors, the absolute position of the robot and a rotation about the gravity vector (yaw) are unobservable. We further augment the state of the developed InEKF with IMU biases, as the online estimation of these parameters has a crucial impact on system performance. We evaluate the convergence of the proposed system with the commonly used quaternion-based EKF observer using a Monte-Carlo simulation. In addition, our experimental evaluation using a Cassie-series bipedal robot shows that the contact-aided InEKF provides better performance in comparison with the quaternion-based EKF as a result of exploiting symmetries present in the system dynamics.

Legged Robot State-Estimation Through Combined Forward Kinematic and Preintegrated Contact Factors

State-of-the-art robotic perception systems have achieved sufficiently good performance using Inertial Measurement Units (IMUs), cameras, and nonlinear optimization techniques, that they are now being deployed as technologies. However, many of these methods rely significantly on vision and often fail when visual tracking is lost due to lighting or scarcity of features. This paper presents a state-estimation technique for legged robots that takes into account the robot's kinematic model as well as its contact with the environment. We introduce forward kinematic factors and preintegrated contact factors into a factor graph framework that can be incrementally solved in real-time. The forward kinematic factor relates the robot's base pose to a contact frame through noisy encoder measurements. The preintegrated contact factor provides odometry measurements of this contact frame while accounting for possible foot slippage. Together, the two developed factors constrain the graph optimization problem allowing the robot's trajectory to be estimated. The paper evaluates the method using simulated and real sensory IMU and kinematic data from experiments with a Cassie-series robot designed by Agility Robotics. These preliminary experiments show that using the proposed method in addition to IMU decreases drift and improves localization accuracy, suggesting that its use can enable successful recovery from a loss of visual tracking.

Gaussian Process Autonomous Mapping and Exploration for Range Sensing Mobile Robots

Most of the existing robotic exploration schemes use occupancy grid representations and geometric targets known as frontiers. The occupancy grid representation relies on the assumption of independence between grid cells and ignores structural correlations present in the environment. We develop a Gaussian Processes (GPs) occupancy mapping technique that is computationally tractable for online map building due to its incremental formulation and provides a continuous model of uncertainty over the map spatial coordinates. The standard way to represent geometric frontiers extracted from occupancy maps is to assign binary values to each grid cell. We extend this notion to novel probabilistic frontier maps computed efficiently using the gradient of the GP occupancy map. We also propose a mutual information-based greedy exploration technique built on that representation that takes into account all possible future observations. A major advantage of high-dimensional map inference is the fact that such techniques require fewer observations, leading to a faster map entropy reduction during exploration for map building scenarios. Evaluations using the publicly available datasets show the effectiveness of the proposed framework for robotic mapping and exploration tasks.

Sampling-based Incremental Information Gathering with Applications to Robotic Exploration and Environmental Monitoring

In this article, we propose a sampling-based motion planning algorithm equipped with an information-theoretic convergence criterion for incremental informative motion planning. The proposed approach allows dense map representations and incorporates the full state uncertainty into the planning process. The problem is formulated as a constrained maximization problem. Our approach is built on rapidly-exploring information gathering algorithms and benefits from advantages of sampling-based optimal motion planning algorithms. We propose two information functions and their variants for fast and online computations. We prove an information-theoretic convergence for an entire exploration and information gathering mission based on the least upper bound of the average map entropy. A natural automatic stopping criterion for information-driven motion control results from the convergence analysis. We demonstrate the performance of the proposed algorithms using three scenarios: comparison of the proposed information functions and sensor configuration selection, robotic exploration in unknown environments, and a wireless signal strength monitoring task in a lake from a publicly available dataset collected using an autonomous surface vehicle.

Sparse Bayesian Inference for Dense Semantic Mapping

Despite impressive advances in simultaneous localization and mapping, dense robotic mapping remains challenging due to its inherent nature of being a high-dimensional inference problem. In this paper, we propose a dense semantic robotic mapping technique that exploits sparse Bayesian models, in particular, the relevance vector machine, for high-dimensional sequential inference. The technique is based on the principle of automatic relevance determination and produces sparse models that use a small subset of the original dense training set as the dominant basis. The resulting map posterior is continuous, and queries can be made efficiently at any resolution. Moreover, the technique has probabilistic outputs per semantic class through Bayesian inference. We evaluate the proposed relevance vector semantic map using publicly available benchmark datasets, NYU Depth V2 and KITTI; and the results show promising improvements over the state-of-the-art techniques.

Gaussian Processes Semantic Map Representation

In this paper, we develop a high-dimensional map building technique that incorporates raw pixelated semantic measurements into the map representation. The proposed technique uses Gaussian Processes (GPs) multi-class classification for map inference and is the natural extension of GP occupancy maps from binary to multi-class form. The technique exploits the continuous property of GPs and, as a result, the map can be inferred with any resolution. In addition, the proposed GP Semantic Map (GPSM) learns the structural and semantic correlation from measurements rather than resorting to assumptions, and can flexibly learn the spatial correlation as well as any additional non-spatial correlation between map points. We extend the OctoMap to Semantic OctoMap representation and compare with the GPSM mapping performance using NYU Depth V2 dataset. Evaluations of the proposed technique on multiple partially labeled RGBD scans and labels from noisy image segmentation show that the GP semantic map can handle sparse measurements, missing labels in the point cloud, as well as noise corrupted labels.

Gaussian Processes Online Observation Classification for RSSI-based Low-cost Indoor Positioning Systems

In this paper, we propose a real-time classification scheme to cope with noisy Radio Signal Strength Indicator (RSSI) measurements utilized in indoor positioning systems. RSSI values are often converted to distances for position estimation. However due to multipathing and shadowing effects, finding a unique sensor model using both parametric and non-parametric methods is highly challenging. We learn decision regions using the Gaussian Processes classification to accept measurements that are consistent with the operating sensor model. The proposed approach can perform online, does not rely on a particular sensor model or parameters, and is robust to sensor failures. The experimental results achieved using hardware show that available positioning algorithms can benefit from incorporating the classifier into their measurement model as a meta-sensor modeling technique.