In this paper we address the simultaneous collision detection and force estimation problem for quadrupedal locomotion using joint encoder information and the robot dynamics only. We design an interacting multiple-model Kalman filter (IMM-KF) that estimates the external force exerted on the robot and multiple possible contact modes. The method is invariant to any gait pattern design. Our approach leverages pseudo-measurement information of the external forces based on the robot dynamics and encoder information. Based on the estimated contact mode and external force, we design a reflex motion and an admittance controller for the swing leg to avoid collisions by adjusting the leg's reference motion. Additionally, we implement a force-adaptive model predictive controller to enhance balancing. Simulation ablatation studies and experiments show the efficacy of the approach.

We address the magnetic-field simulteanous localization and mapping (SLAM) problem for global positioning. We leverage a previously-developed particle filter (PF)-based framework for online Bayesian inference and learning of Gaussian Process state-space models (GP-SSMs). We extend the framework to directly incorporate physical properties of the magnetic field in the GP formulation, by leveraging that magnetic fields under the absence of free currents are curl free. Because of its flexibility, the method can include any motion model that can be expressed by a general nonlinear function, with potential applications to, e.g., mobile robotics and pedestrian localization. Simulation results indicate that our method performs similar to recent batch methods for magnetic-field slam, while the computation times are feasible for online implementations.

We propose a method for joint estimation of a host vehicle state and a map of the road based on global navigation satellite system (GNSS) and camera measurements. We model the road using a spline representation described by a parameter vector having a Gaussian prior representing the uncertainty of the prior map. Both GNSS and camera measurements, such as lane-mark measurements, have noise characteristics that vary in time. To adapt to the changing noise levels and hence improve positioning performance, we combine the sensor information in an interacting multiple-model (IMM) setting to choose the best combination of the estimators with the vehicle state and the parameter vector of the map as the state vector. In a simulation study, we compare vehicle models with varying complexity, and on a real road segment we show that the proposed method can accurately adjust to changing noise conditions and correct for errors in the prior map.

We consider the object recognition problem in autonomous driving using automotive radar sensors. Comparing to Lidar sensors, radar is cost-effective and robust in all- weather conditions for perception in autonomous driving. However, radar signals suffer from low angular resolution and precision in recognizing surrounding objects. To enhance the capacity of automotive radar, in this work, we exploit the temporal information from successive ego-centric bird-eye-view radar image frames for radar object recognition. We leverage the consistency of an object's existence and attributes (size, orientation, etc.), and propose a temporal relational layer to explicitly model the relations between objects within successive radar images. In both object detection and multiple object tracking, we show the superiority of our method compared to several baseline approaches.

While privacy concerns entice connected and automated vehicles to incorporate on-board federated learning (FL) solutions, an integrated vehicle-to-everything communication with heterogeneous computation power aware learning platform is urgently necessary to make it a reality. Motivated by this, we propose a novel mobility, communication and computation aware online FL platform that uses on-road vehicles as learning agents. Thanks to the advanced features of modern vehicles, the on-board sensors can collect data as vehicles travel along their trajectories, while the on-board processors can train machine learning models using the collected data. To take the high mobility of vehicles into account, we consider the delay as a learning parameter and restrict it to be less than a tolerable threshold. To satisfy this threshold, the central server accepts partially trained models, the distributed roadside units (a) perform downlink multicast beamforming to minimize global model distribution delay and (b) allocate optimal uplink radio resources to minimize local model offloading delay, and the vehicle agents conduct heterogeneous local model training. Using real-world vehicle trace datasets, we validate our FL solutions. Simulation shows that the proposed integrated FL platform is robust and outperforms baseline models. With reasonable local training episodes, it can effectively satisfy all constraints and deliver near ground truth multi-horizon velocity and vehicle-specific power predictions.

This paper introduces a B-spline chained ellipses model representation for extended object tracking (EOT) using high-resolution automotive radar measurements. With offline automotive radar training datasets, the proposed model parameters are learned using the expectation-maximization (EM) algorithm. Then the probabilistic multi-hypothesis tracking (PMHT) along with the unscented transform (UT) is proposed to deal with the nonlinear forward-warping coordinate transformation, the measurement-to-ellipsis association, and the state update step. Numerical validation is provided to verify the effectiveness of the proposed EOT framework with automotive radar measurements.

Motivated by real-world automotive radar measurements that are distributed around object (e.g., vehicles) edges with a certain volume, a novel hierarchical truncated Gaussian measurement model is proposed to resemble the underlying spatial distribution of radar measurements. With the proposed measurement model, a modified random matrix-based extended object tracking algorithm is developed to estimate both kinematic and extent states. In particular, a new state update step and an online bound estimation step are proposed with the introduction of pseudo measurements. The effectiveness of the proposed algorithm is verified in simulations.

This paper is concerned with a study of the different proposed gain-function approximation methods in the feedback particle filter. The feedback particle filter (FPF) has been introduced in a series of papers as a control-oriented, resampling-free, variant of the particle filter. The FPF applies a feedback gain to control each particle, where the gain function is found as a solution to a boundary value problem. Approximate solutions are usually necessary, because closed-form expressions can only be computed in certain special cases. By now there exist a number of different methods to approximate the optimal gain function, but it is unclear which method is preferred over another. This paper provides an analysis of some of the recently proposed gain-approximation methods. We discuss computational and algorithmic complexity, and compare performance using well-known benchmark examples.

The precision of global navigation satellite systems (GNSSs) relies heavily on accurate carrier phase ambiguity resolution. The ambiguities are known to take integer values, but the set of ambiguity values is unbounded. We propose a mixture Kalman filter solution to GNSS ambiguity resolution. By marginalizing out the set of ambiguities and exploiting a likelihood proposal for generating the ambiguities, we can bound the possible values to a tight and dense set of integers, which allows for extracting the integer solution as a maximum-likelihood estimate from a mixture Kalman filter. We verify the efficacy of the approach in simulation including a comparison with a well-known integer least-squares based method. The results indicate that our proposed switched mixture Kalman filter repeatedly finds the correct integers in cases where the other method fails.

Motion planning under differential constraints is one of the canonical problems in robotics. State-of-the-art methods evolve around kinodynamic variants of popular sampling-based algorithms, such as Rapidly-exploring Random Trees (RRTs). However, there are still challenges remaining, for example, how to include complex dynamics while guaranteeing optimality. If the open-loop dynamics are unstable, exploration by random sampling in control space becomes inefficient. We describe CL-RRT#, which leverages ideas from the RRT# algorithm and a variant of the RRT algorithm, which generates trajectories using closed-loop prediction. Planning with closed-loop prediction allows us to handle complex unstable dynamics and avoids the need to find computationally hard steering procedures. The search technique presented in the RRT# algorithm allows us to improve the solution quality by searching over alternative reference trajectories. We show the benefits of the proposed approach on an autonomous-driving scenario.