Anirban Mazumdar

This paper presents novel improvements to the Closed Loop Rapidly exploring Random Trees (CL-RRT) framework for navigating complex three dimensional obstacle environments with fixed wing aircraft. Specifically, we utilize 3D Dubins paths with closed-loop node connections for. The maximum goal-to-go cost is used to discard inefficient nodes, and the constraint is iteratively relaxed over time to account for obstacle density. Finally, the algorithm was demonstrated onboard a small unmanned airplane to validate the real time planning performance using available low cost lightweight hardware components. The improved algorithm, called CL-RRT3D, primarily benefits aircraft in demanding situations that must rapidly plan an efficient path in a complex environment.

Teams of agents offer the potential to defeat higher-performance adversaries by employing intelligent coordination. This work examines how Monte Carlo tree search (MCTS) can be utilized for multi-agent, six-degree-of-freedom (6-DoF) engagements. This work introduces a novel approach to action space selection for known MCTS algorithm frameworks. This enables intelligent coordination for 6-DoF multi-agent adversarial game environments with continuous state and action spaces. Our framework leverages a genetic algorithm to determine subsets of algorithmically generated actions to overcome disadvantaged situations. We quantify the benefits of our proposed approach by examining multi-agent aerial engagements with F-16s and P-51Ds. We compare our approach to uncoordinated pure pursuit and reinforcement learning agents. Our results illustrate that the proposed genome-action-informed MCTS substantially increases the win rate compared to pure pursuit and baseline MCTS. These results hold across both aircraft platforms. In addition, we show how our algorithm can achieve high win rates even when operating at a large maneuverability or speed disadvantage. These results illustrate the benefits of MCTS for coordinating 6-DoF engagements and highlight the benefits of intelligent action space selection.

Trajectory optimization for robotic systems remains a challenging problem. This is especially true for robotic systems featuring nonlinear dynamics and many degrees of freedom. Data-based or model-free diffusion has recently been popularized in the fields of artificial intelligence and trajectory optimization. Model-Based Diffusion provides a data-free method of trajectory optimization, trained at runtime on a system dynamics model, suitable for high-dimensional models. This paper examines how importance sampling can enhance the performance of Model-Based Diffusion for trajectory optimization. We quantify the benefits of importance sampling across three long horizon planning tasks. These results show as much as a 13x improvement in sample efficiency depending on environment and optimization parameters.

OBJECTIVE: Real-time determination of human kinematics and kinetics could advance biomechanics research and enable valuable applications of biofeedback and generalizable exoskeleton control. This work aims to investigate a task-independent, user-independent method for obtaining precise real-time joint state estimation across lower-body joints during a wide variety of tasks. METHODS: We developed a generalizable sensing approach using a suit comprised of inertial measurement units (IMUs) and pressure insoles. With the suit, we collected a dataset of 33 tasks commonly performed during construction and hazardous waste cleanup (N = 10). We then trained deep learning user-independent, task-agnostic models to estimate joint lower-body kinematics and dynamics using only worn sensor data. We likewise computed joint kinematics and dynamics analytically from sensor data to serve as a comparison tool for model results. RESULTS: Our models achieved overall angle estimation root-mean-squared-errors (RMSE) of 6.56±.92°, 8.60±1.01°, 7.58±.89°, and 6.00±.73° compared to 13.9±.1.3°, 15.31±1.0°, 10.76±.70°, and 7.56±.48° via analytical methods at the lower back, hip, knee, and ankle, respectively. Likewise, our models achieved overall normalized moment estimation RMSEs of .207±.069 Nm/kg, .242±.044 Nm/kg, .202±.038 Nm/kg, and .193±.034 Nm/kg compared to .306±.036 Nm/kg, .407±.021 Nm/kg, 1.18 ±.022 Nm/kg, and 1.73±.071 Nm/kg via analytical methods at the lower back, hip, knee, and ankle, respectively. CONCLUSION: These results are comparable to other state-of-the-art wearable sensing systems, establishing deep learning as a viable sensing approach that generalizes to new users and tasks. SIGNIFICANCE: This work shows promise for enabling accurate real-world biomechanical data collection and enhancement of biofeedback systems and wearable robot control.

ABSTRACT: Intelligent drilling control systems depend on accurate models of drilling dynamics to avoid destructive behaviors and boost operational efficiency. While lower-fidelity models offer rapid run-times and straightforward analysis, they suffer from some drawbacks. Specifically, lower-complexity models may lack the fidelity required to capture drill-string nonlinear behavior and multi-degree-of-freedom dynamics. This work proposes the use of a co-simulation environment, PyAnsys, to create a computationally efficient yet high-fidelity framework enabling realistic simulation across varying drilling scenarios. The framework uses both Ansys Parametric Design Language (APDL) and Python within a single programming interface to study drillstring behavior. Ansys finite element (FE) software captures essential behavior such as higher mode drilling dynamics and bit-rock frictional interactions. Python enables the integration and real-time adaptation of control schemes based on evolving downhole conditions. The co-simulation environment can also model the communication delays often encountered in field operations. In this paper, we show how the PyAnsys workflow enables rapid implementation of physical drillstring characteristics, drilling operational parameters, and a velocity weakening bit-rock model into the simulation. Subsequent simulations utilize varying control algorithms to study system stability and achieve stick-slip suppression of the FE model. Preliminary results illustrate the framework's potential for capturing higher order dynamic behaviors. This can provide a valuable tool for performing advanced dynamic analysis and control scheme evaluation in challenging drilling scenarios.

BACKGROUND: Type 2 diabetes (T2DM) is the leading cause of chronic kidney disease (CKD) worldwide. Identifying clinical and laboratory associations with chronic kidney disease (CKD) in type 2 diabetes (T2DM) can help physicians target modifiable risk factors. In light of limited data from India, the CITE (CKD in Indian T2DM Evaluation) study was conducted. METHODS: The multicenter, cross-sectional CITE study included 3,325 patients from 28 centres across India over a three-month period. CKD was defined as a persistent decline in kidney function (eGFR < 60 ml/min/1.73 m² for ≥ 3 months) or an elevated urine albumin-to-creatinine ratio (UACR) in at least two samples. Descriptive statistics summarised patient characteristics, while logistic regression analyses identified significant risk factors for CKD. RESULTS: The prevalence of CKD in T2DM was 32%, with a median patient age of 59.9 years and 60.72% having a T2DM duration > 10 years. Reduced eGFR (< 60 ml/min/1.73 m²) was associated with older age (OR: 2.47, 95% CI 2.11-2.88, P < 0.001), longer T2DM duration (OR: 2.28, 95% CI 1.77-2.93, P < 0.001), higher HbA1c (OR: 1.039, 95% CI 1.001-1.079, P = 0.046), and elevated SBP (OR: 1.005, 95% CI 1.002-1.009, P = 0.003). Macroalbuminuria (UACR > 300 mg/g) was linked to non-vegetarian diet (OR: 1.95, 95% CI: 1.59-2.40, P < 0.001) and tobacco use (OR: 1.42, 95% CI: 1.17-1.73, P < 0.001). CKD increased comorbidity odds. CONCLUSION: The CITE study highlights the prevalence of CKD (32%) in Indian patients with T2DM and identifies clinical and laboratory factors associated with CKD, including age ≥ 60 years, T2DM duration, SBP, HbA1c, tobacco use, non-vegetarian diet, and comorbidities. Longitudinal studies are needed to confirm these associations and evaluate causality.

Human-robot teams in dynamic environments have the potential to leverage robot sensing and intelligence to augment human performance through motion suggestions. More specifically, we examine how humans can use external sensors (fixed or robotic) and a motion planning algorithm to help them navigate environments with dynamic obstacles. The novel human-centric velocity-obstacle (HCVO) algorithm suggests a feasible goal-oriented action while avoiding obstacles. Participants were placed in a custom virtual reality (VR) environment and tasked to follow a dynamic goal while avoiding collisions. We demonstrate, over N = 10 participants, that the HCVO algorithm’s guidance significantly improves safety compared to a base VO algorithm. We then examine the performance of N = 15 participants in three conditions: (1) no assistance/control, (2) a top-down drone-view of the entire environment, and 3) motion planner-informed suggestions. The core contributions of this research include (1) introducing and tuning of a human-centric velocity-obstacle (HCVO) algorithm, (2) demonstrating the benefits of the HCVO algorithm compared to a base VO algorithm, (3) demonstrating the benefits of the HCVO algorithm compared with a standard overhead drone view. Long term, the deployment of effective human-centric motion planners can make people safer from workplace to warzone. Code: https://github.com/ROAMR-GT/HCVO-Game . Video: https://www.youtube.com/watch?v=9ITD1GBBz24 .

Humans operating in dynamic environments with limited visibility are susceptible to collisions with moving objects, occupational hazards, and/or other agents, which can result in personal injuries or fatalities. Most existing research has focused on using vibrotactile cues to address this challenge. In this work, we propose a fundamentally new approach that utilizes variable impedance on an active exoskeleton to guide humans away from hazards and towards safe areas. This framework combines artificial potential fields with current impedance-based theories of exoskeleton control to provide a comprehensive navigational system that is intuitive for human operators. First, we present the mathematical framework to encode information about the locations of obstacles and the safest direction in which to move. Next, we optimize controller parameters in a series of human-subject experiments. Finally, we evaluate the framework in virtual reality on a set of randomly generated obstacle fields in environments where vision is either fully or partially occluded. Our results suggest that the exoskeleton provides significant separation from obstacles and reduced collisions compared to vision alone in conditions where visibility was limited to less than 1.3 m. Our work demonstrates that force-feedback in parallel with a human can improve overall navigation ability in low visibility conditions.

gram-negatives (57.6%).Duration of a catheter(AOR:0.3p value <0 001), previous central venous catheter insertion (AOR:11.9p value <0.001), high white blood cells (AOR:0.31p value <0.001),Rural residence (AOR:1.92p value <0.05), and low Hemoglobin level (AOR:2.78p value <0.05) were independently associated with catheterrelated bloodstream infections.Conclusions: In conclusion, the incidence of catheter-related bloodstream infections among patients on hemodialysis was high with gramnegative predominance.Early fistula must be created to reduce the duration of temporary vascular access.I have no potential conflict of interest to disclose.I did not use generative AI and AI-assisted technologies in the writing process.

Repetitive manual labor tasks involving twisting, bending, and lifting commonly lead to lower back and knee injuries in the workplace. To identify tasks with high injury risk, we recruited N = 9 participants to perform industry-relevant, 2-handed lifts with a 11-kg weight. These included symmetrical/asymmetrical, ascending/descending lifts that varied in start-to-end heights (knee-to-waist and waist-to-shoulder). We used a data-driven musculoskeletal model that combined force and motion data with a muscle activation-informed solver (OpenSim, CEINMS) to estimate 3-dimensional internal joint contact forces (JCFs) in the lower back (L5/S1) and knee. Symmetrical lifting resulted in larger peak JCFs than asymmetrical lifting in both the L5/S1 (+20.2% normal [P < .01], +20.3% shear [P = .001], +20.6% total [P < .01]) and the knee (+39.2% shear [P = .001]), and there were no differences in peak JCFs between ascending versus descending motions. Below-the-waist lifting generated significantly greater JCFs in the L5/S1 and knee than above-the-waist lifts (P < .01). We found a positive correlation between knee and L5/S1 peak total JCFs (R2 = .60, P < .01) across the task space, suggesting motor coordination that favors sharing of load distribution across the trunk and legs during lifting.

Abstract This work explores how to use an unmanned ground vehicle (UGV) to offload the physical burdens of equipment from humans. This work formulates dynamic alignment following and compares it to position-based following techniques. We describe the control strategies of both following methods and implement them in a dynamic simulation and a physical prototype. We test the performance of the two following methods and show that dynamic alignment following can reduce robot positional error and interaction force between the human and the robot. We then analyze the energetics and the performance of the human–UGV team for candidate transportation tasks. The presence of the robot can make some tasks take longer to perform. Nonetheless, the results show that for the candidate tasks, the robot can reduce human average metabolic power and average overall task energy.

This paper introduces a new approach for adding replanning capabilities to the maneuver automaton. We call this approach “maneuver interruption.” Maneuver interruption enables replanning by identifying maneuver segments that are dynamically similar to the current vehicle state. As a result, the vehicle can exit a maneuver if new information emerges or the environment changes. We use machine learning to enhance the performance of maneuver interruption. Specifically, we examine how supervised learning can predict dynamic similarity and utilize the learned network to enable maneuver interruption. A variety of models are compared for their ability to quantify the feasibility of a maneuver-to-maneuver transition. The multilayer perceptron is found to be the most effective at this task and was therefore selected for generating maneuver-to-maneuver transitions for replanning. Additionally, we use Monte Carlo methods and pruning to reduce the transition library size by an order of magnitude with minimal loss in performance. We test learning-enhanced maneuver interruption on obstacle evasion tasks with a medium-fidelity ZOHD Drift flight dynamics model. On randomly generated obstacle fields, maneuver interruption is demonstrated to enable longer collision-free flights at a minor cost to control performance.

The development of multi-axis force sensing ca-pabilities in elastomeric materials has enabled new types of human motion measurement with many potential applications. In this work, we present a new soft insole that enables mobile measurement of ground reaction forces (GRFs) outside of a lab-oratory setting. This insole is based on hybrid shear and normal force detecting (SAND) tactile elements (taxels) consisting of optical sensors optimized for shear sensing and piezoresistive pressure sensors dedicated to normal force measurement. We develop polynomial regression and deep neural network (DNN) GRF prediction models and compare their performance to ground-truth force plate data during two walking experiments. Utilizing a 4-layer DNN, we demonstrate accurate prediction of the anterior-posterior (AP), medial-lateral (ML) and vertical components of the GRF with normalized mean absolute errors (NMAE) of <5.1 %, 4.1 %, and 4.5%, respectively. We also demonstrate the durability of the hybrid SAND insole construction through more than 20,000 cycles of use.

Background: Injectable dulaglutide (D) and oral semaglutide (S) are the two commonly used glucagon like peptide 1 receptor analogues (GLP1-RA), with minimal real-life comparative evidence in Type 2 Diabetes (T2D). Thus, a retrospective, multi-center, cohort study was conducted to compare them.

This paper presents a new approach for autonomous motion planning for aircraft suffering from a loss-of-thrust emergency. Specifically, we show how modifications to the Closed-Loop Rapidly exploring Random Trees (CL-RRT) framework combined with controlled energy dissipation can enable rapid and effective kinodynamic motion planning. This CL-RRT Glide algorithm uses closed-loop prediction not only for node connections but also to estimate the remaining energy and prune infeasible paths. This greatly speeds up the search process, which is essential for emergency situations. In addition, we improve the ability of the gliding aircraft to reach a goal position and energy state. We do so by creating a Dissipative Total Energy Control Scheme (TECS). Dissipative TECS enables the glider to lose excess altitude in order to reach a desired energy level. Simulation results illustrate how the proposed methods enable faster motion planning. We also integrate the system into a small unmanned aerial vehicle system and experimentally demonstrate autonomous glide planning and execution during a motor-failure event. This type of algorithm can primarily benefit unmanned aircraft but can also serve to assist pilots in stressful emergency situations.

The field of wearable robotics has made significant progress toward augmenting human functions from multimodal ambulation to manual lifting tasks. However, most of these systems are designed to be task-specific and only focus on a single type of movement (e.g., ambulation). In this work, we design, fabricate, and characterize a versatile hip exoskeleton testbed for lifting and ambulation tasks. The exoskeleton testbed is actuated with custom-built quasidirect drive actuators. We produce an orthotic interface to transmit high torques and assemble a custom mechatronic control system for the exoskeleton testbed. We also detail controllers for level ground walking, incline walking, and symmetric knee to waist lifting. We quantify the actuator torque tracking performance quantified through benchtop and human experiments. During knee-to-waist cyclic lifting, the powered condition exhibited a 16.7% reduction in net metabolic cost compared to the no exoskeleton condition (three subjects). For additional tasks (inclined walking, level-walking), the device provided metabolic reductions when compared with the unpowered case (single subject). These testbed results illustrate the potential for versatile hip assistance and can be used to design future optimized devices.

Achieving robust and efficient drilling is a critical part of reducing the cost of geothermal energy exploration and extraction. Drilling performance is often evaluated using one or more of three key metrics: depth of cut (DOC), rate of penetration (ROP), and mechanical specific energy (MSE). All three of these quantities are related to each other. DOC refers to the depth a bit penetrates into rock during drilling. This is an important quantity for estimating bit behavior. ROP is the simply the DOC multiplied by the rotational rate, and represents how quickly the drill bit is advancing through the ground. ROP is often the parameter used for drilling control and optimization. Finally, MSE provides insight into drilling efficiency and rock type. MSE calculations rely on ROP, drilling force, and drilling torque. Surface-based sensors at the top of the drill are often used to measure all these quantities. However, top-hole measurements can deviate substantially from the behavior at the bit due to lag, vibrations, and friction. Therefore, relying only on top-hole information can lead to suboptimal drilling control. In this work, we describe recent progress towards estimating ROP, DOC, and MSE using down-hole sensing. We assume down-hole measurements of torque, weight-on-bit (WOB). Our hypothesis is that these measurements can provide more rapid and accurate measures of drilling performance. We show how a multi-layer perceptron (MLP) machine learning algorithm can provide rapid and accurate performance when evaluated on experimental data taken from Sandia’s Hard Rock Drilling Facility. In addition, we implement our algorithms on an embedded system intended to emulate a bottom-hole-assembly for sensing and estimation. Our experimental results show that DOC can be estimated accurately and in real-time. These estimates when combined with measurements for rotary speed, torque, and force can provide improved estimates for ROP and MSE. These results have the potential to enable better drilling assessment, improved control, and extended component lifetimes.

Performing heavy manual lifting jobs can be extremely strenuous, often resulting in high rates of injury at overloaded joints. Lower-body exoskeletons have potential to mitigate this fatigue and injury through targeted joint assistance. A variety of current wearable devices aim to provide this kind of support, but their effects on both directly and indirectly targeted joints have not been fully investigated. In this study, a powered bilateral knee exoskeleton (research device), and passive back exosuit (HeroWear Apex) were compared across 10 individuals through a battery of manual lifting tasks. Metabolic, electromyographic, and subject-reported outcome measure data were used to determine which exoskeleton provided the best assistance for each task type. It was found that the knee exoskeleton significantly reduced metabolic cost by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathbf {9.6\%}$ </tex-math></inline-formula> compared to the no-exoskeleton baseline <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$(\mathbf {p &lt; .05})$ </tex-math></inline-formula> . Both the knee and back exoskeletons reduced activation in up to 6 of the muscles measured (out of 16). Importantly, each device primarily reduced muscle activation around the joint it targeted, not around adjacent joints. These findings suggest that exoskeletons that target the knee or lower back joint during lifting can provide significant assistance in reducing exertion.

Motion primitives enable fast planning for complex and dynamic environments. Adversarial environments pose a particularly challenging and unpredictable scenario. Motion-primitive-based planners have the potential to provide benefit in these types of environments. The key challenge is to design a library of maneuvers that effectively capture the necessary capabilities of the vehicle. This work presents a primitive-based game tree search to solve adversarial games in continuous state and action spaces and applies a reinforcement learning framework to autonomously generate effective primitives for the given task. The results demonstrate the ability of the learning framework to produce maneuvers necessary for competing against adversaries. Furthermore, we propose a method for learning a model to estimate the state-dependent value of each motion primitives and demonstrate how to incorporate this model to increase planning performance under time constraints. Additionally, we compare our primitive-based algorithm against forward simulated methods from existing literature and highlight the benefits of motion primitives.

Motion primitives allow for application of discrete search algorithms to rapidly produce trajectories in complex continuous space. The maneuver automaton (MA) provides an elegant formulation for creating a primitive library based on trims and maneuvers. However, performance is fundamentally limited by the contents of the primitive library. If the library is too sparse, performance can be poor in terms of path cost, whereas a library that is too large can increase run time. This work outlines new methods for using genetic algorithms to prune a primitive library. The proposed methods balance the path cost and planning time while maintaining the reachability of the MA. The genetic algorithm in this paper evaluates and mutates populations of motion primitive libraries to optimize both objectives. We illustrate the performance of these methods with a simulated study using a nonlinear medium-fidelity F-16 model. We optimize a library with the presented algorithm for obstacle-free navigation and a nap-of-the-Earth navigation task. In the obstacle-free navigation task, we show a tradeoff of a 10.16% higher planning cost for a 96.63% improvement in run time. In the nap-of-the-Earth task, we show a tradeoff of a 9.712% higher planning cost for a 92.06% improvement in run time.

Mobile robots can pull payloads far greater than their mass. However, off-road terrain features substantial variation in height, grade, and friction. In addition, temperature changes and precipitation add a time-varying element to the terrain. These effects can cause traction to degrade or fail catastrophically. To maximize tethered payload transport capacity through optimal vehicle traction, unique solutions are required for each surface/condition. This paper presents a system that utilizes a vehicle-mounted, multipurpose manipulator to physically adapt the robot with unique anchors suitable for a particular terrain for autonomous payload transport. Specifically, this work presents "swappable anchors", which can be easily attached/detached to adapt the vehicle using permanent magnets. We present four unique anchor designs, each optimal for a specific surface, and experimentally validate them. The experimental results illustrate how this approach can increase the overall payload capacity of a system on various surfaces by increasing the effective coefficient of friction. We demonstrate how we can use the manipulator to autonomously localize the payload using a visual sensor, attach the payload to the vehicle using a permanent-magnet-based payload key/lock, and enable versatile payload transport capacity.

ABSTRACT Drilling vibrations can cause inefficient drilling and accelerated damage to system components. Therefore, reducing or eliminating such vibrations is a major focus area for natural gas and geothermal drilling applications. One particularly important vibration mode is stick-slip. Stick-slip occurs when the bottom-hole angular velocity starts oscillating while the top hole angular velocity remains relatively constant. This not only causes poor drilling, it is also difficult to detect using surface sensors. In this work, we describe the development and testing of a benchtop drilling system for studying stick-slip dynamics and mitigation. We show how this system can produce stick-slip oscillations. Next, we use this data to formulate a data-driven rock-bit interaction model. This model can be combined with linear systems analysis to predict stick-slip and understand mitigation methods. We describe out instrumentation that enables closed-loop control under simulated communications constraints. We conclude by providing preliminary experimental data on bench-level stick-slip. INTRODUCTION Exploration via autonomous drilling processes for geothermal resources is an important focus area for drilling research. However, to fully realize the clean-energy promise of geothermal energy, key challenges still need to be resolved. Issues arising in the drilling process often originate from a drillstring's increased susceptibility to vibrational oscillations as depths increase. Some examples of drilling vibrations include stick-slip (Navarro-Lopez and Suarez, 2004), bit-bounce (Spanos et al., 1995), and whirl (Jansen, 1991). Torsional oscillations are the focus of this work. Torsional vibrations result in a destructive phenomenon known as stick-slip. Initiated at the bit-rock surface, the drillstring bit experiences large angular velocity oscillations not seen at the surface (Pavone and Desplans, 1994; Besselink et al., 2011; Kessai et al., 2020). Stick-slip results in premature bit wear and drillstring fracture. Stick-slip is a fundamentally nonlinear and unpredictable phenomena. Stick-slip results from the combination of bit-rock interactions and drillstring compliance. As a result, there is a key need for experimental studies of stick-slip dynamics and mitigation.

Human Mesenchymal Stromal Cells (hMSC) have shown promising pre-clinical results by eliciting immunomodulatory effects to alleviate inflammation. In order to further study these effects, consistent and automated expansion platforms are required. Recent theoretical innovations have shown that model-based automated controls can more effectively regulate key nutrient concentrations. However, this previous work did not account for time-varying cell growth and death which resulted in inconsistent modeling and controller performance. To mitigate these effects, we propose a new model with time-varying parameters to track viable, proliferating, and dead cells and their respective growth rates with algorithms to estimate these parameters as functions of our limited measured states. We then propose an updated control architecture (referred to as smooth-controller) to leverage the additional parameters for improved estimation and control. The control objective is to regulate glucose and lactate to fixed setpoints while minimizing total media usage and large flowrate disturbances. Finally, we demonstrate the new control architecture in hMSC expansion with improved lactate setpoint MSE (58% reduction), improved observer MSE (36% for glucose and 20% for lactate), and reduced process disturbance (1 to 0 lactate spikes). Although the smooth-controller 7did not improve cell yield (4.91 × 10⁷ compared to 5.08 × 10⁷), it did reduce media usage to match the reduced growth rate thereby increasing cell yield per mL of fed media (6.3 × 10⁴ to 8.6 × 10⁴).

View Video Presentation: https://doi.org/10.2514/6.2023-0487.vid This paper introduces a method for improving the re-planning ability of the Maneuver Automaton. The maneuver-to-maneuver transition, referred to as "Maneuver Interruption", is enabled by identifying near-identical dynamic states between different maneuvers. Naïve search first identifies viable maneuver connections within the motion primitive library, then the identified connections are pruned using Monte-Carlo simulations. Maneuver Interruption is tested on obstacle evasion tasks using a nonlinear ZOHD Drift model with a motion primitive library generated using reinforcement learning. Through Monte-Carlo simulations, the connection library was pruned to 1.5% of the size of the full library with minimal losses in performance. On randomly generated obstacle fields, Maneuver Interruption has enabled longer collision-free flights at the cost of some trajectory-tracking performance.