Adaptive Attitude Control for Foldable Quadrotors

Recent quadrotor vehicles transcended conventional designs, emphasizing more on foldable and reconfigurable bodies. However, the state of the art still focuses on the mechanical feasibility of such designs with limited discussions on the tracking performance of the vehicle during configuration switching. In this paper, we propose a complete control and planning framework for attitude tracking during configuration switching and curbs any switch-based disturbances, which can lead to violation of safety constraints and cause crashes. The control framework includes a morphology-aware adaptive controller with a estimator to account for parameter variation and a minimum-jerk trajectory planner to achieve stable flights while switching. Stability analysis for attitude tracking is presented by employing the theory of switched systems and simulation results validate the proposed framework for a foldable quadrotor's flight through a passageway.

Approximating Discontinuous Nash Equilibrial Values of Two-Player General-Sum Differential Games

Finding Nash equilibrial policies for two-player differential games requires solving Hamilton-Jacobi-Isaacs PDEs. Recent studies achieved success in circumventing the curse of dimensionality in solving such PDEs with underlying applications to human-robot interactions (HRI), by adopting self-supervised (physics-informed) neural networks as universal value approximators. This paper extends from previous SOTA on zero-sum games with continuous values to general-sum games with discontinuous values, where the discontinuity is caused by that of the players' losses. We show that due to its lack of convergence proof and generalization analysis on discontinuous losses, the existing self-supervised learning technique fails to generalize and raises safety concerns in an autonomous driving application. Our solution is to first pre-train the value network on supervised Nash equilibria, and then refine it by minimizing a loss that combines the supervised data with the PDE and boundary conditions. Importantly, the demonstrated advantage of the proposed learning method against purely supervised and self-supervised approaches requires careful choice of the neural activation function: Among $\texttt{relu}$, $\texttt{sin}$, and $\texttt{tanh}$, we show that $\texttt{tanh}$ is the only choice that achieves optimal generalization and safety performance. Our conjecture is that $\texttt{tanh}$ (similar to $\texttt{sin}$) allows continuity of value and its gradient, which is sufficient for the convergence of learning, and at the same time is expressive enough (similar to $\texttt{relu}$) at approximating discontinuous value landscapes. Lastly, we apply our method to approximating control policies for an incomplete-information interaction and demonstrate its contribution to safe interactions.

Invariant Extended Kalman Filtering for Human Motion Estimation with Imperfect Sensor Placement

This paper introduces a new invariant extended Kalman filter design that produces real-time state estimates and rapid error convergence for the estimation of the human body movement even in the presence of sensor misalignment and initial state estimation errors. The filter fuses the data returned by an inertial measurement unit (IMU) attached to the body (e.g., pelvis or chest) and a virtual measurement of zero stance-foot velocity (i.e., leg odometry). The key novelty of the proposed filter lies in that its process model meets the group affine property while the filter explicitly addresses the IMU placement error by formulating its stochastic process model as Brownian motions and incorporating the error in the leg odometry. Although the measurement model is imperfect (i.e., it does not possess an invariant observation form) and thus its linearization relies on the state estimate, experimental results demonstrate fast convergence of the proposed filter (within 0.2 seconds) during squatting motions even under significant IMU placement inaccuracy and initial estimation errors.

Design and Evaluation of an Invariant Extended Kalman Filter for Trunk Motion Estimation with Sensor Misalignment

Understanding human motion is of critical importance for health monitoring and control of assistive robots, yet many human kinematic variables cannot be directly or accurately measured by wearable sensors. In recent years, invariant extended Kalman filtering (InEKF) has shown a great potential in nonlinear state estimation, but its applications to human poses new challenges, including imperfect placement of wearable sensors and inaccurate measurement models. To address these challenges, this paper proposes an augmented InEKF design which considers the misalignment of the inertial sensor at the trunk as part of the states and preserves the group affine property for the process model. Personalized lower-extremity forward kinematic models are built and employed as the measurement model for the augmented InEKF. Observability analysis for the new InEKF design is presented. The filter is evaluated with three subjects in squatting, rolling-foot walking, and ladder-climbing motions. Experimental results validate the superior performance of the proposed InEKF over the state-of-the-art InEKF. Improved accuracy and faster convergence in estimating the velocity and orientation of human, in all three motions, are achieved despite the significant initial estimation errors and the uncertainties associated with the forward kinematic measurement model.

A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds

Degradation models play an important role in Blind super-resolution (SR). The classical degradation model, which mainly involves blur degradation, is too simple to simulate real-world scenarios. The recently proposed practical degradation model includes a full spectrum of degradation types, but only considers complex cases that use all degradation types in the degradation process, while ignoring many important corner cases that are common in the real world. To address this problem, we propose a unified gated degradation model to generate a broad set of degradation cases using a random gate controller. Based on the gated degradation model, we propose simple baseline networks that can effectively handle non-blind, classical, practical degradation cases as well as many other corner cases. To fairly evaluate the performance of our baseline networks against state-of-the-art methods and understand their limits, we introduce the performance upper bound of an SR network for every degradation type. Our empirical analysis shows that with the unified gated degradation model, the proposed baselines can achieve much better performance than existing methods in quantitative and qualitative results, which are close to the performance upper bounds.

A Soft-Bodied Aerial Robot for Collision Resilience and Contact-Reactive Perching

Compared to their biological counterparts, aerial robots demonstrate limited capabilities when tasked to interact in unstructured environments. Very often, the limitation lies in their inability to tolerate collisions and to successfully land, or perch, on objects of unknown shape. Over the past years, efforts to address this have introduced designs that incorporate mechanical impact protection and grasping/perching structures at the cost of reduced agility and flight time due to added weight and bulkiness. In this work, we develop a fabric-based, soft-bodied aerial robot (SoBAR) composed of both contact-reactive perching and embodied impact protection structures while remaining lightweight and streamlined. The robot is capable to 1) pneumatically vary its body stiffness for collision resilience and 2) utilize a hybrid fabric-based, bistable (HFB) grasper to perform passive grasping. When compared to conventional rigid drone frames the SoBAR successfully demonstrates its ability to dissipate impact from head-on collisions and maintain flight stability without any structural damage. Furthermore, in dynamic perching scenarios the HFB grasper is capable to convert impact energy upon contact into firm grasp through rapid body shape conforming in less than 4ms. We exhaustively study and offer insights for this novel perching scheme through grasping characterization, grasp wrench analysis, and experimental grasping validations in objects with various shapes. Finally, we demonstrate the complete control pipeline for SoBAR to approach an object, dynamically perch on it, recover from it, and land.

Event Detection Explorer: An Interactive Tool for Event Detection Exploration

Event Detection (ED) is an important task in natural language processing. In the past few years, many datasets have been introduced for advancing ED machine learning models. However, most of these datasets are under-explored because not many tools are available for people to study events, trigger words, and event mention instances systematically and efficiently. In this paper, we present an interactive and easy-to-use tool, namely ED Explorer, for ED dataset and model exploration. ED Explorer consists of an interactive web application, an API, and an NLP toolkit, which can help both domain experts and non-experts to better understand the ED task. We use ED Explorer to analyze a recent proposed large-scale ED datasets (referred to as MAVEN), and discover several underlying problems, including sparsity, label bias, label imbalance, and debatable annotations, which provide us with directions to improve the MAVEN dataset. The ED Explorer can be publicly accessed through http://edx.leafnlp.org/. The demonstration video is available here https://www.youtube.com/watch?v=6QPnxPwxg50.

Probabilistic Consensus on Feature Distribution for Multi-robot Systems with Markovian Exploration Dynamics

In this paper, we present a consensus-based decentralized multi-robot approach to reconstruct a discrete distribution of features, modeled as an occupancy grid map, that represent information contained in a bounded planar environment, such as visual cues used for navigation or semantic labels associated with object detection. The robots explore the environment according to a random walk modeled by a discrete-time discrete-state (DTDS) Markov chain and estimate the feature distribution from their own measurements and the estimates communicated by neighboring robots, using a distributed Chernoff fusion protocol. We prove that under this decentralized fusion protocol, each robot's feature distribution converges to the actual distribution in an almost sure sense. We verify this result in numerical simulations that show that the Hellinger distance between the estimated and actual feature distributions converges to zero over time for each robot. We also validate our strategy through Software-In-The-Loop (SITL) simulations of quadrotors that search a bounded square grid for a set of visual features distributed on a discretized circle.

Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima

This paper considers incremental few-shot learning, which requires a model to continually recognize new categories with only a few examples provided. Our study shows that existing methods severely suffer from catastrophic forgetting, a well-known problem in incremental learning, which is aggravated due to data scarcity and imbalance in the few-shot setting. Our analysis further suggests that to prevent catastrophic forgetting, actions need to be taken in the primitive stage -- the training of base classes instead of later few-shot learning sessions. Therefore, we propose to search for flat local minima of the base training objective function and then fine-tune the model parameters within the flat region on new tasks. In this way, the model can efficiently learn new classes while preserving the old ones. Comprehensive experimental results demonstrate that our approach outperforms all prior state-of-the-art methods and is very close to the approximate upper bound. The source code is available at https://github.com/moukamisama/F2M.