Hierarchical Meta-learning-based Adaptive Controller

We study how to design learning-based adaptive controllers that enable fast and accurate online adaptation in changing environments. In these settings, learning is typically done during an initial (offline) design phase, where the vehicle is exposed to different environmental conditions and disturbances (e.g., a drone exposed to different winds) to collect training data. Our work is motivated by the observation that real-world disturbances fall into two categories: 1) those that can be directly monitored or controlled during training, which we call "manageable", and 2) those that cannot be directly measured or controlled (e.g., nominal model mismatch, air plate effects, and unpredictable wind), which we call "latent". Imprecise modeling of these effects can result in degraded control performance, particularly when latent disturbances continuously vary. This paper presents the Hierarchical Meta-learning-based Adaptive Controller (HMAC) to learn and adapt to such multi-source disturbances. Within HMAC, we develop two techniques: 1) Hierarchical Iterative Learning, which jointly trains representations to caption the various sources of disturbances, and 2) Smoothed Streaming Meta-Learning, which learns to capture the evolving structure of latent disturbances over time (in addition to standard meta-learning on the manageable disturbances). Experimental results demonstrate that HMAC exhibits more precise and rapid adaptation to multi-source disturbances than other adaptive controllers.

Model Predictive Control for Aggressive Driving Over Uneven Terrain

Terrain traversability in off-road autonomy has traditionally relied on semantic classification or resource-intensive dynamics models to capture vehicle-terrain interactions. However, our experiences in the development of a high-speed off-road platform have revealed several critical challenges that are not adequately addressed by current methods at our operating speeds of 7--10 m/s. This study focuses particularly on uneven terrain geometries such as hills, banks, and ditches. These common high-risk geometries are capable of disabling the vehicle and causing severe passenger injuries if poorly traversed. We introduce a physics-based framework for identifying traversability constraints on terrain dynamics. Using this framework, we then derive two fundamental constraints, with a primary focus on mitigating rollover and ditch-crossing failures. In addition, we present the design of our planning and control system, which uses Model Predictive Control (MPC) and a low-level controller to enable the fast and efficient computation of these constraints to meet the demands of our aggressive driving. Through real-world experimentation and traversal of hills and ditches, our approach is tested and benchmarked against a human expert. These results demonstrate that our approach captures fundamental elements of safe and aggressive control on these terrain features.

DATT: Deep Adaptive Trajectory Tracking for Quadrotor Control

Precise arbitrary trajectory tracking for quadrotors is challenging due to unknown nonlinear dynamics, trajectory infeasibility, and actuation limits. To tackle these challenges, we present Deep Adaptive Trajectory Tracking (DATT), a learning-based approach that can precisely track arbitrary, potentially infeasible trajectories in the presence of large disturbances in the real world. DATT builds on a novel feedforward-feedback-adaptive control structure trained in simulation using reinforcement learning. When deployed on real hardware, DATT is augmented with a disturbance estimator using L1 adaptive control in closed-loop, without any fine-tuning. DATT significantly outperforms competitive adaptive nonlinear and model predictive controllers for both feasible smooth and infeasible trajectories in unsteady wind fields, including challenging scenarios where baselines completely fail. Moreover, DATT can efficiently run online with an inference time less than 3.2 ms, less than 1/4 of the adaptive nonlinear model predictive control baseline

Safe Deep Policy Adaptation

A critical goal of autonomy and artificial intelligence is enabling autonomous robots to rapidly adapt in dynamic and uncertain environments. Classic adaptive control and safe control provide stability and safety guarantees but are limited to specific system classes. In contrast, policy adaptation based on reinforcement learning (RL) offers versatility and generalizability but presents safety and robustness challenges. We propose SafeDPA, a novel RL and control framework that simultaneously tackles the problems of policy adaptation and safe reinforcement learning. SafeDPA jointly learns adaptive policy and dynamics models in simulation, predicts environment configurations, and fine-tunes dynamics models with few-shot real-world data. A safety filter based on the Control Barrier Function (CBF) on top of the RL policy is introduced to ensure safety during real-world deployment. We provide theoretical safety guarantees of SafeDPA and show the robustness of SafeDPA against learning errors and extra perturbations. Comprehensive experiments on (1) classic control problems (Inverted Pendulum), (2) simulation benchmarks (Safety Gym), and (3) a real-world agile robotics platform (RC Car) demonstrate great superiority of SafeDPA in both safety and task performance, over state-of-the-art baselines. Particularly, SafeDPA demonstrates notable generalizability, achieving a 300% increase in safety rate compared to the baselines, under unseen disturbances in real-world experiments.

Guardians as You Fall: Active Mode Transition for Safe Falling

Recent advancements in optimal control and reinforcement learning have enabled quadrupedal robots to perform various agile locomotion tasks over diverse terrains. During these agile motions, ensuring the stability and resiliency of the robot is a primary concern to prevent catastrophic falls and mitigate potential damages. Previous methods primarily focus on recovery policies after the robot falls. There is no active safe falling solution to the best of our knowledge. In this paper, we proposed Guardians as You Fall (GYF), a safe falling/tumbling and recovery framework that can actively tumble and recover to stable modes to reduce damage in highly dynamic scenarios. The key idea of GYF is to adaptively traverse different stable modes via active tumbling before the robot shifts to irrecoverable poses. Via comprehensive simulation and real-world experiments, we show that GYF significantly reduces the maximum acceleration and jerk of the robot base compared to the baselines. In particular, GYF reduces the maximum acceleration and jerk by 20%~73% in different scenarios in simulation and real-world experiments. GYF offers a new perspective on safe falling and recovery in locomotion tasks, potentially enabling much more aggressive explorations of existing agile locomotion skills.

Deep Model Predictive Optimization

A major challenge in robotics is to design robust policies which enable complex and agile behaviors in the real world. On one end of the spectrum, we have model-free reinforcement learning (MFRL), which is incredibly flexible and general but often results in brittle policies. In contrast, model predictive control (MPC) continually re-plans at each time step to remain robust to perturbations and model inaccuracies. However, despite its real-world successes, MPC often under-performs the optimal strategy. This is due to model quality, myopic behavior from short planning horizons, and approximations due to computational constraints. And even with a perfect model and enough compute, MPC can get stuck in bad local optima, depending heavily on the quality of the optimization algorithm. To this end, we propose Deep Model Predictive Optimization (DMPO), which learns the inner-loop of an MPC optimization algorithm directly via experience, specifically tailored to the needs of the control problem. We evaluate DMPO on a real quadrotor agile trajectory tracking task, on which it improves performance over a baseline MPC algorithm for a given computational budget. It can outperform the best MPC algorithm by up to 27% with fewer samples and an end-to-end policy trained with MFRL by 19%. Moreover, because DMPO requires fewer samples, it can also achieve these benefits with 4.3X less memory. When we subject the quadrotor to turbulent wind fields with an attached drag plate, DMPO can adapt zero-shot while still outperforming all baselines. Additional results can be found at https://tinyurl.com/mr2ywmnw.

Aerial Interaction with Tactile Sensing

While autonomous Uncrewed Aerial Vehicles (UAVs) have grown rapidly, most applications only focus on passive visual tasks. Aerial interaction aims to execute tasks involving physical interactions, which offers a way to assist humans in high-risk, high-altitude operations, thereby reducing cost, time, and potential hazards. The coupled dynamics between the aerial vehicle and manipulator, however, pose challenges for precision control. Previous research has typically employed either position control, which often fails to meet mission accuracy, or force control using expensive, heavy, and cumbersome force/torque sensors that also lack local semantic information. Conversely, tactile sensors, being both cost-effective and lightweight, are capable of sensing contact information including force distribution, as well as recognizing local textures. Existing work on tactile sensing mainly focuses on tabletop manipulation tasks within a quasi-static process. In this paper, we pioneer the use of vision-based tactile sensors on a fully-actuated UAV to improve the accuracy of the more dynamic aerial manipulation tasks. We introduce a pipeline utilizing tactile feedback for real-time force tracking via a hybrid motion-force controller and a method for wall texture detection during aerial interactions. Our experiments demonstrate that our system can effectively replace or complement traditional force/torque sensors, improving flight performance by approximately 16% in position tracking error when using the fused force estimate compared to relying on a single sensor. Our tactile sensor achieves 93.4% accuracy in real-time texture recognition and 100% post-contact. To the best of our knowledge, this is the first work to incorporate a vision-based tactile sensor into aerial interaction tasks.

CAJun: Continuous Adaptive Jumping using a Learned Centroidal Controller

We present CAJun, a novel hierarchical learning and control framework that enables legged robots to jump continuously with adaptive jumping distances. CAJun consists of a high-level centroidal policy and a low-level leg controller. In particular, we use reinforcement learning (RL) to train the centroidal policy, which specifies the gait timing, base velocity, and swing foot position for the leg controller. The leg controller optimizes motor commands for the swing and stance legs according to the gait timing to track the swing foot target and base velocity commands using optimal control. Additionally, we reformulate the stance leg optimizer in the leg controller to speed up policy training by an order of magnitude. Our system combines the versatility of learning with the robustness of optimal control. By combining RL with optimal control methods, our system achieves the versatility of learning while enjoys the robustness from control methods, making it easily transferable to real robots. We show that after 20 minutes of training on a single GPU, CAJun can achieve continuous, long jumps with adaptive distances on a Go1 robot with small sim-to-real gaps. Moreover, the robot can jump across gaps with a maximum width of 70cm, which is over 40% wider than existing methods.

Optimal Exploration for Model-Based RL in Nonlinear Systems

Learning to control unknown nonlinear dynamical systems is a fundamental problem in reinforcement learning and control theory. A commonly applied approach is to first explore the environment (exploration), learn an accurate model of it (system identification), and then compute an optimal controller with the minimum cost on this estimated system (policy optimization). While existing work has shown that it is possible to learn a uniformly good model of the system~\citep{mania2020active}, in practice, if we aim to learn a good controller with a low cost on the actual system, certain system parameters may be significantly more critical than others, and we therefore ought to focus our exploration on learning such parameters. In this work, we consider the setting of nonlinear dynamical systems and seek to formally quantify, in such settings, (a) which parameters are most relevant to learning a good controller, and (b) how we can best explore so as to minimize uncertainty in such parameters. Inspired by recent work in linear systems~\citep{wagenmaker2021task}, we show that minimizing the controller loss in nonlinear systems translates to estimating the system parameters in a particular, task-dependent metric. Motivated by this, we develop an algorithm able to efficiently explore the system to reduce uncertainty in this metric, and prove a lower bound showing that our approach learns a controller at a near-instance-optimal rate. Our algorithm relies on a general reduction from policy optimization to optimal experiment design in arbitrary systems, and may be of independent interest. We conclude with experiments demonstrating the effectiveness of our method in realistic nonlinear robotic systems.