M. Ani Hsieh

Advances in real‐time data processing have enabled robot teams to continuously adapt their sampling locations as they monitor their environments, enabling them to build highly predictive models of complex, dynamic environments. These models, in turn, enable robots to make better plans and more quickly adapt to changing environmental conditions. However, continuously identifying high information content regions and assigning robots to these new locations requires addressing the long‐standing multi‐robot task allocation problem. Existing allocation methods use task‐specific planning and/or control strategies that lack the flexibility needed to monitor spatiotemporal environments. In contrast, biological collectives robustly handle a wide range of environment conditions by relying on resource selection mechanisms that are beneficial to the survival of the population. Taking inspiration from biology, we address the challenge of flexibly monitoring spatiotemporal environments by using a team‐wide macroscopic ensemble approach which naturally mimics biological selection techniques. Existing macroscopic allocation strategies enable robots to switch between sampling regions, but unlike biological counterparts cannot respond to changing environmental conditions and perform poorly when team sizes are small. In this work, we introduce an online adaptive macroscopic allocation strategy that leverages environmental feedback to enable adaptation to changing environmental conditions. Our approach results in the synthesis of single‐agent task selection policies that achieves flexible assignment of robots for a range of dynamic conditions that perform well even when team sizes are small.

Salps are underwater invertebrates considered to be among the world's most energy-efficient examples of jet propulsion. They can swim as solitary individuals or as physically connected colonies, coordinating their jets to produce collective movement. Inspired by salps, we developed the SALP (Salp-inspired Approach to Low-energy Propulsion) system, where individual SALP robots can be physically connected into a multi-SALP group, and we investigate the coupled effects of physical arrangement and jet coordination on the swimming performance and energy efficiency of a two-SALP system. We conduct free swimming tests to evaluate locomotion performance metrics and find that the two-SALP system, when properly coordinated, is able to swim with 15.7% higher speed and 11.3% lower cost of transport than the single SALP. Supporting flow characterization experiments using particle image velocimetry reveal vortex ring structures emanating from robot SALP nozzles. The data suggest that propulsion performance is affected by the spatial arrangement of the vortex ring structure. In particular, we find that SALP systems that produce a parallel vortex ring arrangement produce less vortex circulation and impulse than an in-series vortex ring arrangement. Overall, the SALP system is a useful platform for exploring salp-inspired multi-jet locomotion strategies, enabling decoupling of physical and control parameters to expose underlying locomotion physics in ways that are difficult with the biological salp. These insights advance our understanding of multi-jet locomotion and support the development of more energy-efficient jet-propelled underwater robots in the future.

Source localization in a complex flow poses a significant challenge for multi-robot teams tasked with localizing the source of chemical leaks or tracking the dispersion of an oil spill. The flow dynamics can be time-varying and chaotic, resulting in sporadic and intermittent sensor readings, and complex environmental geometries further complicate a team's ability to model and predict the dispersion. To accurately account for the physical processes that drive the dispersion dynamics, robots must have access to computationally intensive numerical models, which can be difficult when onboard computation is limited. We present a distributed mobile sensing framework for source localization in which each robot carries a machine-learned, finite element model of its environment to guide information-based sampling. The models are used to evaluate an approximate mutual information criterion to drive an infotaxis control strategy, which selects sensing regions that are expected to maximize informativeness for the source localization objective. Our approach achieves faster error reduction compared to baseline sensing strategies and results in more accurate source localization compared to baseline machine learning approaches.

We present a machine learning framework for adaptive source localization in which agents use a structure-preserving digital twin of a coupled hydrodynamic-transport system for real-time trajectory planning and data assimilation. The twin is constructed with conditional neural Whitney forms (CNWF), coupling the numerical guarantees of finite element exterior calculus (FEEC) with transformer-based operator learning. The resulting model preserves discrete conservation, and adapts in real time to streaming sensor data. It employs a conditional attention mechanism to identify: a reduced Whitney-form basis; reduced integral balance equations; and a source field, each compatible with given sensor measurements. The induced reduced-order environmental model retains the stability and consistency of standard finite-element simulation, yielding a physically realizable, regular mapping from sensor data to the source field. We propose a staggered scheme that alternates between evaluating the digital twin and applying Lloyd's algorithm to guide sensor placement, with analysis providing conditions for monotone improvement of a coverage functional. Using the predicted source field as an importance function within an optimal-recovery scheme, we demonstrate recovery of point sources under continuity assumptions, highlighting the role of regularity as a sufficient condition for localization. Experimental comparisons with physics-agnostic transformer architectures show improved accuracy in complex geometries when physical constraints are enforced, indicating that structure preservation provides an effective inductive bias for source identification.

This paper introduces a novel multiobjective human-in-the-loop planning algorithm for information-driven path planning. We formulate the path planning problem as a multiobjective orienteering problem, aiming to optimize multiple survey objectives under operational constraints. Inspired by Indicator-based Fitness Evaluation and Tabu Search, the algorithm efficiently predicts high-scoring paths, which are presented to a human expert for refinement of waypoints. Once data is collected at the next waypoint, the expert updates the objectives of the relevant points of interest, allowing for dynamic adjustments based on evolving survey requirements. Tailored for autonomous geological surveys, we validate our approach with real-world data from Sage Hen, CA. The proposed solver outperforms existing MOOP solvers by achieving better results with lower variance, resulting in improved survey path coverage.

Time-optimal trajectories drive quadrotors to their dynamic limits, but computing such trajectories involves solving non-convex problems via iterative nonlinear optimization, making them prohibitively costly for real-time applications. In this work, we investigate learning-based models that imitate a model-based time-optimal trajectory planner to accelerate trajectory generation. Given a dataset of collision-free geometric paths, we show that modeling architectures can effectively learn the patterns underlying time-optimal trajectories. We introduce a quantitative framework to analyze local analytic properties of the learned models, and link them to the Backward Reachable Tube of the geometric tracking controller. To enhance robustness, we propose a data augmentation scheme that applies random perturbations to the input paths. Compared to classical planners, our method achieves substantial speedups, and we validate its real-time feasibility on a hardware quadrotor platform. Experiments demonstrate that the learned models generalize to previously unseen path lengths. The code for our approach can be found here: https://github.com/maokat12/lbTOPPQuad

Flying quadrotors in tight formations is a challenging problem. It is known that in the near-field airflow of a quadrotor, the aerodynamic effects induced by the propellers are complex and difficult to characterize. Although machine learning tools can potentially be used to derive models that capture these effects, these data-driven approaches can be sample inefficient and the resulting models often do not generalize as well as their first-principles counterparts. In this work, we propose a framework that combines the benefits of first-principles modeling and data-driven approaches to construct an accurate and sample efficient representation of the complex aerodynamic effects resulting from quadrotors flying in formation. The data-driven component within our model is lightweight, making it amenable for optimization-based control design. Through simulations and physical experiments, we show that incorporating the model into a novel learning-based nonlinear model predictive control (MPC) framework results in substantial performance improvements in terms of trajectory tracking and disturbance rejection. In particular, our framework significantly outperforms nominal MPC in physical experiments, achieving a 40.1% improvement in the average trajectory tracking errors and a 57.5% reduction in the maximum vertical separation errors. Our framework also achieves exceptional sample efficiency, using only a total of 46 seconds of flight data for training across both simulations and physical experiments. Furthermore, with our proposed framework, the quadrotors achieve an exceptionally tight formation, flying with an average separation of less than 1.5 body lengths throughout the flight.

As autonomous robotic systems become increasingly mature, users will want to specify missions at the level of intent rather than in low-level detail. Language is an expressive and intuitive medium for such mission specification. However, realizing language-guided robotic teams requires overcoming significant technical hurdles. Interpreting and realizing language-specified missions requires advanced semantic reasoning. Successful heterogeneous robots must effectively coordinate actions and share information across varying viewpoints. Additionally, communication between robots is typically intermittent, necessitating robust strategies that leverage communication opportunities to maintain coordination and achieve mission objectives. In this work, we present a first-of-its-kind system where an unmanned aerial vehicle (UAV) and an unmanned ground vehicle (UGV) are able to collaboratively accomplish missions specified in natural language while reacting to changes in specification on the fly. We leverage a Large Language Model (LLM)-enabled planner to reason over semantic-metric maps that are built online and opportunistically shared between an aerial and a ground robot. We consider task-driven navigation in urban and rural areas. Our system must infer mission-relevant semantics and actively acquire information via semantic mapping. In both ground and air-ground teaming experiments, we demonstrate our system on seven different natural-language specifications at up to kilometer-scale navigation.

The integration of foundation models (FMs) into robotics has enabled robots to understand natural language and reason about the semantics in their environments. However, existing FM-enabled robots primary operate in closed-world settings, where the robot is given a full prior map or has a full view of its workspace. This paper addresses the deployment of FM-enabled robots in the field, where missions often require a robot to operate in large-scale and unstructured environments. To effectively accomplish these missions, robots must actively explore their environments, navigate obstacle-cluttered terrain, handle unexpected sensor inputs, and operate with compute constraints. We discuss recent deployments of SPINE, our LLM-enabled autonomy framework, in field robotic settings. To the best of our knowledge, we present the first demonstration of large-scale LLM-enabled robot planning in unstructured environments with several kilometers of missions. SPINE is agnostic to a particular LLM, which allows us to distill small language models capable of running onboard size, weight and power (SWaP) limited platforms. Via preliminary model distillation work, we then present the first language-driven UAV planner using on-device language models. We conclude our paper by proposing several promising directions for future research.

Accurate and efficient fluid flow models are essential for applications relating to many physical phenomena, including geophysical, aerodynamic, and biological systems. While these flows may exhibit rich and multiscale dynamics, in many cases, underlying low-rank structures exist, which describe the bulk of the motion. These structures tend to be spatially large and temporally slow and may contain most of the energy in a given flow. The extraction and parsimonious representation of these low-rank dynamics from high-dimensional data is a key challenge. Inspired by the success of physics-informed machine learning methods, we propose a spectrally informed approach to extract low-rank models of fluid flows by leveraging known spectral properties in the learning process. We incorporate this knowledge by imposing regularizations on the learned dynamics, which bias the training process toward learning low-frequency structures with corresponding higher power. We demonstrate the effectiveness of this method to improve prediction and produce learned models, which better match the underlying spectral properties of prototypical fluid flows.

This letter addresses the problem of Multi-Robot Simultaneous Localization and Mapping (SLAM) in dynamic feature-free marine environments. Traditional SLAM approaches rely on static environmental features, which are often scarce in marine environments, hindering their applicability in aquatic environments like rivers, lakes, and oceans. We propose a localization and mapping formulation that jointly optimizes robot odometry, relative robot bearings, and estimates of dynamic environmental flow parameters using state-of-the-art parameter estimation techniques like Sparse Identification of Nonlinear Dynamics (SINDy) (Brunton et al., 2016). Our approach not only provides an accurate flow field map but it also enhances pose estimation of multiple minimally actuated robots transported by the flow (Subbaraya et al., 2016), (Molchanov et al., 2015). We showcase our methodology on a series of increasingly dynamically complex flow fields including the Duffing oscillator, the wind-driven double-gyre, and real ocean data from the Gulf of Mexico.

Hurricane Ida struck the U.S. East Coast in August 2021, pushing the Schuylkill River in Philadelphia to a record discharge nearly 100 times larger than its average flow. As one of the most severe disasters of the 21st century, Ida exemplifies the increasing frequency and intensity of extreme hydrometeorological events under climate change. Predicting urban flood pathways remains challenging due to the complex interplay of rainfall-runoff and river–tide–landscape interactions. To address this, we developed a high-resolution (street-resolved) flood model integrating LiDAR terrain data, bathymetric surveys, and land use-based surface friction across Philadelphia. We find that impervious surfaces and fragmented infrastructure exacerbate pluvial flooding and localized waterlogging, increasing exposure for both low- and high-income communities. Scenario-based simulations reveal a tipping point: a logarithmic increase in inundation areas for return periods above 100 years, and 2-7% additional flooding when peak discharge coincides with high tide—rising to up to 15% under projected sea level rise by 2100. Our findings underscore the compounding impacts of climate extremes in urban river systems and the need for integrated forecasting and adaptive planning—particularly in vulnerable, low-lying, and rapidly urbanizing regions worldwide.

In this letter, we address the task of adaptive sampling to model vector fields. When modeling environmental phenomena with a robot, gathering high resolution information can be resource intensive. Actively gathering data and modeling flows with the data is a more efficient alternative. However, in such scenarios, data is often sparse and thus requires flow modeling techniques that are effective at capturing the relevant dynamical features of the flow to ensure high prediction accuracy of the resulting models. To accomplish this effectively, regions with high informative value must be identified. We propose EnKode, an active sampling approach based on Koopman Operator theory and ensemble methods that can build high quality flow models and effectively estimate model uncertainty. For modeling complex flows, EnKode provides comparable or better estimates of unsampled flow regions than Gaussian Process Regression models with hyperparameter optimization. Additionally, our active sensing scheme provides more accurate flow estimates than comparable strategies that rely on uniform sampling. We evaluate EnKode using three common benchmarking systems: the Bickley Jet, Lid-Driven Cavity flow with an obstacle, and real ocean currents from the National Oceanic and Atmospheric Administration (NOAA).

In this letter, we address the task of adaptive sampling to model vector fields. When modeling environmental phenomena with a robot, gathering high resolution information can be resource intensive. Actively gathering data and modeling flows with the data is a more efficient alternative. However, in such scenarios, data is often sparse and thus requires flow modeling techniques that are effective at capturing the relevant dynamical features of the flow to ensure high prediction accuracy of the resulting models. To accomplish this effectively, regions with high informative value must be identified. We propose EnKode, an active sampling approach based on Koopman Operator theory and ensemble methods that can build high quality flow models and effectively estimate model uncertainty. For modeling complex flows, EnKode provides comparable or better estimates of unsampled flow regions than Gaussian Process Regression models with hyperparameter optimization. Additionally, our active sensing scheme provides more accurate flow estimates than comparable strategies that rely on uniform sampling. We evaluate EnKode using three common benchmarking systems: the Bickley Jet, Lid-Driven Cavity flow with an obstacle, and real ocean currents from the National Oceanic and Atmospheric Administration (NOAA).

Communication constraints can significantly impact robots’ ability to share information, coordinate their movements, and synchronize their actions, thus limiting coordination in Multi-Robot Exploration (MRE) applications. In this work, we address these challenges by modeling the MRE application as a DEC-POMDP and designing a joint policy that follows a rendezvous plan. This policy allows robots to explore unknown environments while intermittently sharing maps opportunistically or at rendezvous locations without being constrained by joint path optimizations. To generate the rendezvous plan, robots represent the MRE task as an instance of the Job Shop Scheduling Problem (JSSP) and minimize JSSP metrics. They aim to reduce waiting times and increase connectivity, which correlates to the DEC-POMDP rewards and time to complete the task. Our simulation results suggest that our method is more efficient than using relays or maintaining intermittent communication with a base station, being a suitable approach for Multi-Robot Exploration. We developed a proof-of-concept using the Robot Operating System (ROS) that is available at: https://github.com/multirobotplayground/Noetic-Multi-Robot-Sandbox.

Planning time-optimal trajectories for quadrotors in cluttered environments is a challenging, non-convex problem. This paper addresses minimizing the traversal time of a given collision-free geometric path without violating actuation bounds of the vehicle. Previous approaches have either relied on convex relaxations that do not guarantee dynamic feasibility or have generated overly conservative time parametrizations. We propose TOPPQuad, a time-optimal path parameterization algorithm for quadrotors which explicitly incorporates quadrotor rigid body dynamics and constraints, such as bounds on inputs (including motor thrusts) and state of the vehicle (including the pose, linear and angular velocity and acceleration). We demonstrate the ability of the planner to generate faster trajectories that respect hardware constraints of the robot compared to planners with relaxed notions of dynamic feasibility in both simulation and hardware. We also demonstrate how TOPPQuad can be used to plan trajectories for quadrotors that utilize bidirectional motors. Overall, the proposed approach paves a way towards maximizing the efficacy of autonomous micro aerial vehicles while ensuring their safety.

Flying quadrotors in tight formations is a challenging problem. It is known that in the near-field airflow of a quadrotor, the aerodynamic effects induced by the propellers are complex and difficult to characterize. Although machine learning tools can potentially be used to derive models that capture these effects, these data-driven approaches can be sample inefficient and the resulting models often do not generalize as well as their first-principles counterparts. In this work, we propose a framework that combines the benefits of first-principles modeling and data-driven approaches to construct an accurate and sample efficient representation of the complex aerodynamic effects resulting from quadrotors flying in formation. The data-driven component within our model is lightweight, making it amenable for optimization-based control design. Through simulations and physical experiments, we show that incorporating the model into a novel learning-based nonlinear model predictive control (MPC) framework results in substantial performance improvements in terms of trajectory tracking and disturbance rejection. In particular, our framework significantly outperforms nominal MPC in physical experiments, achieving a 40.1% improvement in the average trajectory tracking errors and a 57.5% reduction in the maximum vertical separation errors. Our framework also achieves exceptional sample efficiency, using only a total of 46 seconds of flight data for training across both simulations and physical experiments. Furthermore, with our proposed framework, the quadrotors achieve an exceptionally tight formation, flying with an average separation of less than 1.5 body lengths throughout the flight. A video illustrating our framework and physical experiments is given here: https://youtu.be/Hv-0JiVoJGo

Coordinating the motion of multiple robots in cluttered environments remains a computationally challenging task. We study the problem of minimizing the execution time of a set of geometric paths by a team of robots with state-dependent actuation constraints. We propose a Time-Optimal Path Parameterization (TOPP) algorithm for multiple car-like agents, where the modulation of the timing of every robot along its assigned path is employed to ensure collision avoidance and dynamic feasibility. This is achieved through the use of a priority queue to determine the order of trajectory execution for each robot while taking into account all possible collisions with higher priority robots in a spatiotemporal graph. We show a 10-20% reduction in makespan against existing state-of-the-art methods and validate our approach through simulations and hardware experiments.

Soft robots have many advantages over rigid robots thanks to their compliant and passive nature. However, it is generally challenging to model the dynamics of soft robots due to their high spatial dimensionality, making it difficult to use model-based methods to accurately control soft robots. It often requires direct numerical simulation of partial differential equations to simulate soft robots. This not only requires an accurate numerical model, but also makes soft robot modeling slow and expensive. Deep learning algorithms have shown promises in data-driven modeling of soft robots. However, these algorithms usually require a large amount of data, which are difficult to obtain in either simulation or real-world experiments of soft robots. In this work, we propose KNODE-Cosserat, a framework that combines first-principle physics models and neural ordinary differential equations. We leverage the best from both worlds -- the generalization ability of physics-based models and the fast speed of deep learning methods. We validate our framework in both simulation and real-world experiments. In both cases, we show that the robot model significantly improves over the baseline models under different metrics.

Multi-robot collaboration in large-scale environments with limited-sized teams and without external infrastructure is challenging, since the software framework required to support complex tasks must be robust to unreliable and intermittent communication links. In this work, we present MOCHA (Multi-robot Opportunistic Communication for Heterogeneous Collaboration), a framework for resilient multi-robot collaboration that enables large-scale exploration in the absence of continuous communications. MOCHA is based on a gossip communication protocol that allows robots to interact opportunistically whenever communication links are available, propagating information on a peer-to-peer basis. We demonstrate the performance of MOCHA through real-world experiments with commercial-off-the-shelf (COTS) communication hardware. We further explore the system’s scalability in simulation, evaluating the performance of our approach as the number of robots increases and communication ranges vary. Finally, we demonstrate how MOCHA can be tightly integrated with the planning stack of autonomous robots. We show a communication-aware planning algorithm for a high-altitude aerial robot executing a collaborative task while maximizing the amount of information shared with ground robots.The source code for MOCHA and the high-altitude UAV planning system is available open source <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>.

One common and desirable application of robots is exploring potentially hazardous and unstructured environments. Air-ground collaboration offers a synergistic approach to addressing such exploration challenges. In this paper, we demonstrate a system for large-scale exploration using a team of aerial and ground robots. Our system uses semantics as lingua franca, and relies on fully opportunistic communications. We highlight the unique challenges from this approach, explain our system architecture and showcase lessons learned during our experiments. All our code is open-source, encouraging researchers to use it and build upon.

The construction of bifurcation diagrams is an essential component of understanding nonlinear dynamical systems. The task can be challenging when one knows the equations of the dynamical system and becomes much more difficult if only the underlying data associated with the system are available. In this work, we present a transformer-based method to directly estimate the bifurcation diagram using only noisy data associated with an arbitrary dynamical system. By splitting a bifurcation diagram into segments at bifurcation points, the transformer is trained to simultaneously predict how many segments are present and to minimize the loss with respect to the predicted position, shape, and asymptotic stability of each predicted segment. The trained model is shown, both quantitatively and qualitatively, to reliably estimate the structure of the bifurcation diagram for arbitrarily generated one- and two-dimensional systems experiencing a codimension-one bifurcation with as few as 30 trajectories. We show that the method is robust to noise in both the state variable and the system parameter.

With the increase in data availability, it has been widely demonstrated that neural networks (NN) can capture complex system dynamics precisely in a data-driven manner. However, the architectural complexity and nonlinearity of the NNs make it challenging to synthesize a provably safe controller. In this work, we propose a novel safety filter that relies on convex optimization to ensure safety for a NN system, subject to additive disturbances that are capable of capturing modeling errors. Our approach leverages tools from NN verification to over-approximate NN dynamics with a set of linear bounds, followed by an application of robust linear MPC to search for controllers that can guarantee robust constraint satisfaction. We demonstrate the efficacy of the proposed framework numerically on a nonlinear pendulum system.

Nonlinear model predictive control (MPC) is an established control framework that not only provides a systematic way to handle state and input constraints, but also offers the flexibility to incorporate data-driven models. With the proliferation of machine learning techniques, there is an uptrend in the development of learning-based MPC, with neural networks (NN) being an important cornerstone. Although it has been shown that NNs are expressive enough to model the dynamics of complex systems and produce accurate state predictions, these predictions often do not include uncertainty estimates or have practical finite sample guarantees. In contrast to existing work that either requires the data samples to be exchangeable or relies on properties of the underlying data distribution, we propose an approach that utilizes weighted conformal prediction to alleviate these assumptions and to synthesize provably valid, finite-sample uncertainty estimates for data-driven dynamics models, in a distribution-free manner. These uncertainty estimates are generated online and incorporated into a novel uncertainty-aware learning-based MPC framework. Through a case study with a cartpole system controlled by a state-of-the-art learning-based MPC framework, we demonstrate that our approach not only provides well- calibrated uncertainty estimates, but also enhances the closed- loop performance of the system.

This paper addresses the problem of reaching con-sensus under input saturation and intermittent communication, which can hinder the convergence of the system. We propose a method that translates the consensus into an equivalent stability problem. Then, we compute bounded sets that enclose the initial conditions and the evolution of trajectories leading to local input-to-state stability for systems interconnected over directed intermittent topologies. Our contributions include sufficient conditions for stability and stabilization of multi-agent systems under intermittent interactions and saturating inputs, with the ability to evaluate disturbance tolerance and rejection based on the regions that enclose the system's trajectories. We define disturbance rejection in terms of the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathscr{L}_{2}$</tex> gain, and formulate stability and controller design conditions as convex optimization problems. Our method enable the maximization of regions that ensure local input-to-state stability, we provide numerical examples highlighting the tradeoffs between mean frequency of intermittent interactions, disturbance energy, and convergence region size.

With the rapidly changing climate and an increase in extreme weather events, it is necessary to have better methods to monitor and study the impacts of these phenomena on urban river environments. Multi-robot environmental monitoring has long focused on strategies that assign individual robots to distinct regions or task objectives. While these methods have seen success for Autonomous Surface Vehicles (ASVs), the spatial expanse and temporal variability of rivers impose an increased burden on existing techniques, necessitating computationally intensive replanning. Alternative methods aim to model and control teams of robots by prescribing global constraints on the system, using the insight that robots' transitions between tasks are stochastic and time-based. These methods do not require replanning because robots will perform different tasks achieving the overall desired system state, focusing on temporal switching alone limits their overall descriptive power. In this paper, we present a method that considers collaborations between robots to inform task switching based on spatial proximity. Our results suggest that in unknown environments macroscopic models provide increased flexibility for individual robot task execution as compared to coverage control methods.

The recent increase in data availability and reliability has led to a surge in the development of learning-based model predictive control (MPC) frameworks for robot systems. Despite attaining substantial performance improvements over their non-learning counterparts, many of these frameworks rely on an offline learning procedure to synthesize a dynamics model. This implies that uncertainties encountered by the robot during deployment are not accounted for in the learning process. On the other hand, learning-based MPC methods that learn dynamics models online are computationally expensive and often require a significant amount of data. To alleviate these shortcomings, we propose a novel learning-enhanced MPC framework that incorporates components from C <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</inf> adaptive control into learning-based MPC. This integration enables the accurate compensation of both matched and unmatched uncertainties in a sample-efficient way, enhancing the control performance during deployment. In our proposed framework, we present two variants and apply them to the control of a quadrotor system. Through simulations and physical experiments, we demonstrate that the proposed framework not only allows the synthesis of an accurate dynamics model on-the-fly, but also significantly improves the closed-loop control performance under a wide range of spatio-temporal uncertainties.

Autonomous Marine Vehicles (AMVs) have gained interest for scientific and commercial applications, including pipeline and algae bloom monitoring, contaminant tracking, and ocean debris removal. The Team Orienteering Problem (TOP) is relevant in this context as Multi-Robot Systems (MRSs) allow for better coverage of the area of interest, simultaneous data collection at different locations, and an increase in the overall robustness and efficiency of the mission. However, route planning for AMVs in dynamic ocean environments is challenging due to the coupling of environmental and vehicle dynamics. We propose a multi-objective formulation that accounts for the trade-offs between visiting multiple task locations and energy consumption by the vehicles subject to a time budget. This work focuses on vehicles that can maintain a constant net speed but can be adapted to vehicles with constant thrust. Different from existing approaches, our method is able to leverage time-varying ocean currents to improve the energy efficiency of resulting routes. We validate our approach experimentally by superimposing ocean flow models with benchmark instances of the TOP.

Multi-robot collaboration in large-scale environments with limited-sized teams and without external infrastructure is challenging, since the software framework required to support complex tasks must be robust to unreliable and intermittent communication links. In this work, we present MOCHA (Multi-robot Opportunistic Communication for Heterogeneous Collaboration), a framework for resilient multi-robot collaboration that enables large-scale exploration in the absence of continuous communications. MOCHA is based on a gossip communication protocol that allows robots to interact opportunistically whenever communication links are available, propagating information on a peer-to-peer basis. We demonstrate the performance of MOCHA through real-world experiments with commercial-off-the-shelf (COTS) communication hardware. We further explore the system's scalability in simulation, evaluating the performance of our approach as the number of robots increases and communication ranges vary. Finally, we demonstrate how MOCHA can be tightly integrated with the planning stack of autonomous robots. We show a communication-aware planning algorithm for a high-altitude aerial robot executing a collaborative task while maximizing the amount of information shared with ground robots. The source code for MOCHA and the high-altitude UAV planning system is available open source: http://github.com/KumarRobotics/MOCHA, http://github.com/KumarRobotics/air_router.

Planning time-optimal trajectories for quadrotors in cluttered environments is a challenging, non-convex problem. This paper addresses minimizing the traversal time of a given collision-free geometric path without violating bounds on individual motor thrusts of the vehicle. Previous approaches have either relied on convex relaxations that do not guarantee dynamic feasibility, or have generated overly conservative time parametrizations. We propose TOPPQuad, a time-optimal path parameterization algorithm for quadrotors which explicitly incorporates quadrotor rigid body dynamics and constraints such as bounds on inputs (including motor speeds) and state of the vehicle (including the pose, linear and angular velocity and acceleration). We demonstrate the ability of the planner to generate faster trajectories that respect hardware constraints of the robot compared to several planners with relaxed notions of dynamic feasibility. We also demonstrate how TOPPQuad can be used to plan trajectories for quadrotors that utilize bidirectional motors. Overall, the proposed approach paves a way towards maximizing the efficacy of autonomous micro aerial vehicles while ensuring their safety.

With the increase in data availability, it has been widely demonstrated that neural networks (NN) can capture complex system dynamics precisely in a data-driven manner. However, the architectural complexity and nonlinearity of the NNs make it challenging to synthesize a provably safe controller. In this work, we propose a novel safety filter that relies on convex optimization to ensure safety for a NN system, subject to additive disturbances that are capable of capturing modeling errors. Our approach leverages tools from NN verification to over-approximate NN dynamics with a set of linear bounds, followed by an application of robust linear MPC to search for controllers that can guarantee robust constraint satisfaction. We demonstrate the efficacy of the proposed framework numerically on a nonlinear pendulum system.