arXiv subjects

Stefano Di Cairano

Publications and source records attributed to Stefano Di Cairano.

At least 19 recordsLinked to original sources

arXiv2026

Autonomous Navigation and Station-Keeping on Near-Rectilinear Halo Orbits

This article develops an optical navigation (OPNAV) and station-keeping pipeline for the near-rectilinear halo orbit (NRHO) in high-fidelity ephemeris model dynamics, using synthetic images of the Moon in a non-iterative horizon-based OPNAV algorithm, applying the result in a navigation filter, and using the obtained estimates in a station-keeping control scheme that keeps the spacecraft in the vicinity of a reference orbit. We study differential correction-based and minimization-based implementations of the so-called x-axis and propose an improved targeting prediction scheme by incorporating the filter's state covariance with an unscented transform. We also introduce a hysteresis mechanism, which improves stationkeeping cost and provides insight into the difference in performance between the differential correction-based and minimization-based approaches. We perform Monte-Carlo experiments to assess the pipeline's tracking and Delta-V performances. We report several key findings, including the variability of the filter performance with the sensor field of view and measurement locations, station-keeping cost reduction achieved by the unscented transform-based prediction and hysteresis, as well as the variability of the cumulative Delta-V as a function of maneuver location due to the periodic structure in the OPNAV-based filter's estimation accuracy.

eess.SY↗

arXiv2026

RoboAtlas: Contextual Active SLAM

We present RoboAtlas, a contextual Active SLAM framework that adaptively balances geometric exploration and semantic reasoning using a scalable 3D semantic mapping system, OpenRoboVox. RoboAtlas integrates frontier exploration, global semantic-map reasoning, and egocentric VLM-based reasoning through a contextual multi-armed bandit that transitions from exploration to semantically guided navigation as scene understanding improves. We evaluate the system in simulation and on a Unitree Go2 robot in large-scale real-world environments exceeding 1800 m2 with approx. 30k mapped semantic instances, achieving a 100% task success rate. On the GOAT-Bench "Val Unseen" benchmark, RoboAtlas achieves state-of-the-art performance with highest reported success rate (SR) of 90.6%, using GPT-4o, improving over the strongest prior baseline by 17.8 percentage points in SR. Using the much smaller Qwen2.5-VL-7B model, it still achieves 88.8% SR, outperforming all baselines using GPT-4o in SR, and revealing the importance of the information gained by our semantic mapping framework over simply replacing the underlying foundation model. The results demonstrate that grounding foundation models with large-scale 3D semantic maps enables robust and efficient contextual Active SLAM.

cs.RO↗

arXiv2026

Data-driven Spatial Classification using Multi-Arm Bandits for Monitoring with Energy-Constrained Mobile Robots

We consider the spatial classification problem for monitoring using data collected by a coordinated team of mobile robots. Such classification problems arise in several applications including search-and-rescue and precision agriculture. Specifically, we want to classify the regions of a search environment into interesting and uninteresting as quickly as possible using a team of mobile sensors and mobile charging stations. We develop a data-driven strategy that accommodates the noise in sensed data and the limited energy capacity of the sensors, and generates collision-free motion plans for the team. We propose a bi-level approach, where a high-level planner leverages a multi-armed bandit framework to determine the potential regions of interest for the drones to visit next based on the data collected online. Then, a low-level path planner based on integer programming coordinates the paths for the team to visit the determined regions subject to the physical constraints. We characterize several theoretical properties of the proposed approach, including anytime guarantees and task completion time. We show the efficacy of our approach in simulation, and further validate these observations in physical experiments using mobile robots.

cs.RO↗

arXiv2026

MOBIUS: A Multi-Modal Bipedal Robot that can Walk, Crawl, Climb, and Roll

This paper presents the MOBIUS platform, a bipedal robot capable of walking, crawling, climbing, and rolling. MOBIUS features four limbs, two 6-DoF arms with two-finger grippers for manipulation and climbing, and two 4-DoF legs for locomotion--enabling smooth transitions across diverse terrains without reconfiguration. A hybrid control architecture combines reinforcement learning for locomotion and force control for compliant contact interactions during manipulation. A high-level MIQCP planner autonomously selects locomotion modes to balance stability and energy efficiency. Hardware experiments demonstrate robust gait transitions, dynamic climbing, and full-body load support via pinch grasp. Overall, MOBIUS demonstrates the importance of tight integration between morphology, high-level planning, and control to enable mobile loco-manipulation and grasping, substantially expanding its interaction capabilities, workspace, and traversability.

cs.RO↗

arXiv2026

Safe Whole-Body Loco-Manipulation via Combined Model and Learning-based Control

Simultaneous locomotion and manipulation enables robots to interact with their environment beyond the constraints of a fixed base. However, coordinating legged locomotion with arm manipulation, while considering safety and compliance during contact interaction remains challenging. To this end, we propose a whole-body controller that combines a model-based admittance control for the manipulator arm with a Reinforcement Learning (RL) policy for legged locomotion. The admittance controller maps external wrenches--such as those applied by a human during physical interaction--into desired end-effector velocities, allowing for compliant behavior. The velocities are tracked jointly by the arm and leg controllers, enabling a unified 6-DoF force response. The model-based design permits accurate force control and safety guarantees via a Reference Governor (RG), while robustness is further improved by a Kalman filter enhanced with neural networks for reliable base velocity estimation. We validate our approach in both simulation and hardware using the Unitree Go2 quadruped robot with a 6-DoF arm and wrist-mounted 6-DoF Force/Torque sensor. Results demonstrate accurate tracking of interaction-driven velocities, compliant behavior, and safe, reliable performance in dynamic settings.

cs.RO↗

arXiv2026

PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning

Robotic imitation learning typically requires models that capture multimodal action distributions while operating at real-time control rates and accommodating multiple sensing modalities. Although recent generative approaches such as diffusion models, flow matching, and Implicit Maximum Likelihood Estimation (IMLE) have achieved promising results, they often satisfy only a subset of these requirements. To address this, we introduce PRISM, a single-pass policy based on a batch-global rejection-sampling variant of IMLE. PRISM couples a temporal multisensory encoder (integrating RGB, depth, tactile, audio, and proprioception) with a linear-attention generator using a Performer architecture. We demonstrate the efficacy of PRISM on a diverse real-world hardware suite, including loco-manipulation using a Unitree Go2 with a 7-DoF arm D1 and tabletop manipulation with a UR5 manipulator. Across challenging physical tasks such as pre-manipulation parking, high-precision insertion, and multi-object pick-and-place, PRISM outperforms state-of-the-art diffusion policies by 10-25% in success rate while maintaining high-frequency (30-50 Hz) closed-loop control. We further validate our approach on large-scale simulation benchmarks, including CALVIN, MetaWorld, and Robomimic. In CALVIN (10% data split), PRISM improves success rates by approximately 25% over diffusion and approximately 20% over flow matching, while simultaneously reducing trajectory jerk by 20x-50x. These results position PRISM as a fast, accurate, and multisensory imitation policy that retains multimodal action coverage without the latency of iterative sampling.

cs.RO↗

arXiv2025

Set-based Optimal, Robust, and Resilient Control with Applications to Autonomous Precision Landing

We present a real-time-capable set-based framework for closed-loop predictive control of autonomous systems using tools from computational geometry, dynamic programming, and convex optimization. The control architecture relies on the offline precomputation of the controllable tube, i.e, a time-indexed sequence of controllable sets. Sets are represented using constrained zonotopes (CZs), which are efficient encodings of convex polytopes that support fast set operations and enable tractable dynamic programming in high dimensions. Online, we obtain a globally optimal control profile by solving a series of one-step optimal control problems. Our key contributions are: (1) free-final-time optimality: we devise an optimal horizon computation algorithm to achieve global optimality; (2) robustness: we handle stochastic uncertainty in both the state and control, with probabilistic guarantees, by constructing bounded disturbance sets; (3) resilience: we develop (i) an optimization-free approach to computing the instantaneous reachable set, i.e., the reachable set from the current state, to enable, for example, large/maximal divert maneuvers, and (ii) an approach to achieving maximal decision-deferral, i.e., maintaining reachability/divert-feasibility to multiple targets for as long as possible. By means of an autonomous precision landing case study, we demonstrate globally optimal free-final-time guidance, robustness to navigation and actuation uncertainties, instantaneous divert envelope computation, and maximal decision-deferral.

math.OC↗

arXiv2025

Revolution-Spaced Output-Feedback Model Predictive Control for Station Keeping on Near-Rectilinear Halo Orbits

We develop a model predictive control (MPC) policy for station keeping on a Near-Rectilinear Halo Orbit (NRHO). The proposed policy achieves full-state tracking of a reference NRHO via a multiple-maneuver control horizon, each spaced one revolution apart to abide by typical mission operation requirements. We prove that the proposed policy is recursively feasible, and perform numerical evaluation in an output-feedback setting by incorporating a navigation filter and realistic operational uncertainties, where the proposed MPC is compared against the state-of-the-art station-keeping algorithm adopted for the Gateway. Our approach successfully maintains the spacecraft in the vicinity of the reference NRHO at a similar cumulative cost as existing station-keeping methods without encountering phase deviation issues, a common drawback of existing methods with one maneuver per revolution.

eess.SY↗

arXiv2025

Data-Driven Motion Planning for Uncertain Nonlinear Systems

This paper proposes a data-driven motion-planning framework for nonlinear systems that constructs a sequence of overlapping invariant polytopes. Around each randomly sampled waypoint, the algorithm identifies a convex admissible region and solves data-driven linear-matrix-inequality problems to learn several ellipsoidal invariant sets together with their local state-feedback gains. The convex hull of these ellipsoids, still invariant under a piece-wise-affine controller obtained by interpolating the gains, is then approximated by a polytope. Safe transitions between nodes are ensured by verifying the intersection of consecutive convex-hull polytopes and introducing an intermediate node for a smooth transition. Control gains are interpolated in real time via simplex-based interpolation, keeping the state inside the invariant polytopes throughout the motion. Unlike traditional approaches that rely on system dynamics models, our method requires only data to compute safe regions and design state-feedback controllers. The approach is validated through simulations, demonstrating the effectiveness of the proposed method in achieving safe, dynamically feasible paths for complex nonlinear systems.

eess.SY↗

arXiv2025

Energy-Efficient Motion Planner for Legged Robots

We propose an online motion planner for legged robot locomotion with the primary objective of achieving energy efficiency. The conceptual idea is to leverage a placement set of footstep positions based on the robot's body position to determine when and how to execute steps. In particular, the proposed planner uses virtual placement sets beneath the hip joints of the legs and executes a step when the foot is outside of such placement set. Furthermore, we propose a parameter design framework that considers both energy-efficiency and robustness measures to optimize the gait by changing the shape of the placement set along with other parameters, such as step height and swing time, as a function of walking speed. We show that the planner produces trajectories that have a low Cost of Transport (CoT) and high robustness measure, and evaluate our approach against model-free Reinforcement Learning (RL) and motion imitation using biological dog motion priors as the reference. Overall, within low to medium velocity range, we show a 50.4% improvement in CoT and improved robustness over model-free RL, our best performing baseline. Finally, we show ability to handle slippery surfaces, gait transitions, and disturbances in simulation and hardware with the Unitree A1 robot.

cs.RO↗

arXiv2025

Delayed Expansion AGT: Kinodynamic Planning with Application to Tractor-Trailer Parking

Kinodynamic planning of articulated vehicles in cluttered environments faces additional challenges arising from high-dimensional state space and complex system dynamics. Built upon [1],[2], this work proposes the DE-AGT algorithm that grows a tree using pre-computed motion primitives (MPs) and A* heuristics. The first feature of DE-AGT is a delayed expansion of MPs. In particular, the MPs are divided into different modes, which are ranked online. With the MP classification and prioritization, DE-AGT expands the most promising mode of MPs first, which eliminates unnecessary computation and finds solutions faster. To obtain the cost-to-go heuristic for nonholonomic articulated vehicles, we rely on supervised learning and train neural networks for fast and accurate cost-to-go prediction. The learned heuristic is used for online mode ranking and node selection. Another feature of DE-AGT is the improved goal-reaching. Exactly reaching a goal state usually requires a constant connection checking with the goal by solving steering problems -- non-trivial and time-consuming for articulated vehicles. The proposed termination scheme overcomes this challenge by tightly integrating a light-weight trajectory tracking controller with the search process. DE-AGT is implemented for autonomous parking of a general car-like tractor with 3-trailer. Simulation results show an average of 10x acceleration compared to a previous method.

cs.RO↗

arXiv2025

Successive Convexification for Passively-Safe Spacecraft Rendezvous on Near Rectilinear Halo Orbit

We present an optimization-based approach for fuel-efficient spacecraft rendezvous to the Gateway, a space station that will be deployed on a near rectilinear halo orbit (NRHO) around the Moon. The approach: i) ensures passive safety and satisfies path constraints at all times, ii) meets the specifications for critical decision points along the trajectory, iii) accounts for uncertainties that are common in real-world operation, such as due to orbital insertion, actuation, and navigation measurement, via chance constraints and utilizes a stabilizing feedback controller to bound the effect of uncertainties. We leverage sequential convex programming (SCP) and isoperimetric reformulation of path constraints, including passive safety, to eliminate the risk of inter-sample constraint violations that is common in existing methods. We demonstrate the proposed approach on a realistic simulation of a rendezvous to the Gateway.

math.OC↗

arXiv2025

Simultaneous Collision Detection and Force Estimation for Dynamic Quadrupedal Locomotion

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

cs.RO↗

arXiv2025

A Comparative Study of MINLP and MPVC Formulations for Solving Complex Nonlinear Decision-Making Problems in Aerospace Applications

High-level decision-making for dynamical systems often involves performance and safety specifications that are activated or deactivated depending on conditions related to the system state and commands. Such decision-making problems can be naturally formulated as optimization problems where these conditional activations are regulated by discrete variables. However, solving these problems can be challenging numerically, even on powerful computing platforms, especially when the dynamics are nonlinear. In this work, we consider decision-making for nonlinear systems where certain constraints, as well as possible terms in the cost function, are activated or deactivated depending on the system state and commands. We show that these problems can be formulated either as mixed-integer nonlinear programs (MINLPs) or as mathematical programs with vanishing constraints (MPVCs), where the former formulation involves discrete decision variables, whereas the latter relies on continuous variables subject to structured nonconvex constraints. We discuss the different solution methods available for both formulations and demonstrate them on optimal trajectory planning problems in various aerospace applications. Finally, we compare the strengths and weaknesses of the MINLP and MPVC approaches through a focused case study on powered descent guidance with divert-feasible regions.

math.OC↗

arXiv2025

Projection-free computation of robust controllable sets with constrained zonotopes

We study the problem of computing robust controllable sets for discrete-time linear systems with additive uncertainty. We propose a tractable and scalable approach to inner- and outer-approximate robust controllable sets using constrained zonotopes, when the additive uncertainty set is a symmetric, convex, and compact set. Our least-squares-based approach uses novel closed-form approximations of the Pontryagin difference between a constrained zonotopic minuend and a symmetric, convex, and compact subtrahend. Unlike existing approaches, our approach does not rely on convex optimization solvers, and is projection-free for ellipsoidal and zonotopic uncertainty sets. We also propose a least-squares-based approach to compute a convex, polyhedral outer-approximation to constrained zonotopes, and characterize sufficient conditions under which all these approximations are exact. We demonstrate the computational efficiency and scalability of our approach in several case studies, including the design of abort-safe rendezvous trajectories for a spacecraft in near-rectilinear halo orbit under uncertainty. Our approach can inner-approximate a 20-step robust controllable set for a 100-dimensional linear system in under 15 seconds on a standard computer.

math.OC↗

arXiv2024

Path Planning and Motion Control for Accurate Positioning of Car-like Robots

This paper investigates the planning and control for accurate positioning of car-like robots. We propose a solution that integrates two modules: a motion planner, facilitated by the rapidly-exploring random tree algorithm and continuous-curvature (CC) steering technique, generates a CC trajectory as a reference; and a nonlinear model predictive controller (NMPC) regulates the robot to accurately track the reference trajectory. Based on the $μ$-tangency conditions in prior art, we derive explicit existence conditions and develop associated computation methods for a special class of CC paths which not only admit the same driving patterns as Reeds-Shepp paths but also consist of cusp-free clothoid turns. Afterwards, we create an autonomous vehicle parking scenario where the NMPC endeavors to follow the reference trajectory. Feasibility and computational efficiency of the CC steering are validated by numerical simulation. CarSim-Simulink joint simulations statistically verify that with exactly same NMPC, the closed-loop system with CC trajectories as references substantially outperforms the case where Reeds-Shepp trajectories are used as references.

cs.RO↗

arXiv2024

Equivariant Deep Learning of Mixed-Integer Optimal Control Solutions for Vehicle Decision Making and Motion Planning

Mixed-integer quadratic programs (MIQPs) are a versatile way of formulating vehicle decision making and motion planning problems, where the prediction model is a hybrid dynamical system that involves both discrete and continuous decision variables. However, even the most advanced MIQP solvers can hardly account for the challenging requirements of automotive embedded platforms. Thus, we use machine learning to simplify and hence speed up optimization. Our work builds on recent ideas for solving MIQPs in real-time by training a neural network to predict the optimal values of integer variables and solving the remaining problem by online quadratic programming. Specifically, we propose a recurrent permutation equivariant deep set that is particularly suited for imitating MIQPs that involve many obstacles, which is often the major source of computational burden in motion planning problems. Our framework comprises also a feasibility projector that corrects infeasible predictions of integer variables and considerably increases the likelihood of computing a collision-free trajectory. We evaluate the performance, safety and real-time feasibility of decision-making for autonomous driving using the proposed approach on realistic multi-lane traffic scenarios with interactive agents in SUMO simulations.

cs.RO↗

arXiv2023

Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning

We consider the problem of safe multi-agent motion planning for drones in uncertain, cluttered workspaces. For this problem, we present a tractable motion planner that builds upon the strengths of reinforcement learning and constrained-control-based trajectory planning. First, we use single-agent reinforcement learning to learn motion plans from data that reach the target but may not be collision-free. Next, we use a convex optimization, chance constraints, and set-based methods for constrained control to ensure safety, despite the uncertainty in the workspace, agent motion, and sensing. The proposed approach can handle state and control constraints on the agents, and enforce collision avoidance among themselves and with static obstacles in the workspace with high probability. The proposed approach yields a safe, real-time implementable, multi-agent motion planner that is simpler to train than methods based solely on learning. Numerical simulations and experiments show the efficacy of the approach.

cs.RO↗