STEM: Semantic Target Search and Exploration using MAVs in Cluttered Environments

Autonomous target search is crucial for deploying Micro Aerial Vehicles (MAVs) in emergency response and rescue missions. Existing approaches either focus on 2D semantic navigation in structured environments -- which is less effective in complex 3D settings, or on robotic exploration in cluttered spaces -- which often lacks the semantic reasoning needed for efficient target search. This paper overcomes these limitations by proposing a novel framework that utilizes a semantically-guided viewpoint planner to minimize target search and exploration time in unstructured 3D environments using an MAV. Specifically, we develop a combinatorial planner that generates efficient semantic exploration plans by prioritizing viewpoints that likely lead to the target. To guide the planner towards the target, an active perception pipeline is developed that propagates semantic priorities of observed objects into neighboring frontier voxels for computing semantic information gains of frontier viewpoints. In addition, we demonstrate how LLM-based similarity scores can be leveraged as semantic priority input to our pipeline. Evaluations in two distinct simulation environments show that the proposed method consistently outperforms baselines by quickly finding the target while maintaining reasonable exploration times. Real-world experiments with an MAV further demonstrate the method's ability to handle practical constraints like limited battery life, small sensor range, and semantic uncertainty.

Coordinated Diffusion: Generating Multi-Agent Behavior Without Multi-Agent Demonstrations

Imitation learning powered by generative models has proven effective for modeling complex single-agent behaviors. However, teaching multi-agent systems, like multiple arms or vehicles, to coordinate through imitation learning is hindered by a fundamental data bottleneck: as the joint state-action space grows exponentially with the number of agents, collecting a sufficient amount of coordinated multi-agent demonstrations becomes extremely costly. In this work, we ask: how can we leverage single-agent demonstration data to learn multi-agent policies? We present Coordinated Diffusion (CoDi), a framework that couples independently trained single-agent diffusion policies through a user-defined multi-agent cost function, without requiring any coordinated demonstrations. We derive a new diffusion-based sampling scheme wherein the diffusion score function decomposes into independent, single-agent pre-trained base policies plus a cost-driven guidance term that coordinates these base policies into cohesive multi-agent behavior. We show that this guidance term can be estimated in a gradient-free manner, making CoDi applicable to black-box, non-differentiable cost functions without additional training. Theoretically and empirically, we analyze the conditions under which this composition can faithfully approximate a target multi-agent behavior. We find a complementary role for demonstration data versus the cost function: single-agent demonstrations must cover the support of the desired multi-agent behavior, while the cost function must promote desired behavior from this product of single-agent policies. Our results in simulation and hardware experiments of a two-arm manipulation task show that CoDi discovers robust coordinated behavior from single-agent data, is more data-efficient than multi-agent baselines, and highlights the importance of joint guidance, base policy support, and cost design.

Strategizing at Speed: A Learned Model Predictive Game for Multi-Agent Drone Racing

Autonomous drone racing pushes the boundaries of high-speed motion planning and multi-agent strategic decision-making. Success in this domain requires drones not only to navigate at their limits but also to anticipate and counteract competitors' actions. In this paper, we study a fundamental question that arises in this domain: how deeply should an agent strategize before taking an action? To this end, we compare two planning paradigms: the Model Predictive Game (MPG), which finds interaction-aware strategies at the expense of longer computation times, and contouring Model Predictive Control (MPC), which computes strategies rapidly but does not reason about interactions. We perform extensive experiments to study this trade-off, revealing that MPG outperforms MPC at moderate velocities but loses its advantage at higher speeds due to latency. To address this shortcoming, we propose a Learned Model Predictive Game (LMPG) approach that amortizes model predictive gameplay to reduce latency. In both simulation and hardware experiments, we benchmark our approach against MPG and MPC in head-to-head races, finding that LMPG outperforms both baselines.

From Data to Safe Mobile Robot Navigation: An Efficient and Modular Robust MPC Design Pipeline

Model predictive control (MPC) is a powerful strategy for planning and control in autonomous mobile robot navigation. However, ensuring safety in real-world deployments remains challenging due to the presence of disturbances and measurement noise. Existing approaches often rely on idealized assumptions, neglect the impact of noisy measurements, and simply heuristically guess unrealistic bounds. In this work, we present an efficient and modular robust MPC design pipeline that systematically addresses these limitations. The pipeline consists of an iterative procedure that leverages closed-loop experimental data to estimate disturbance bounds and synthesize a robust output-feedback MPC scheme. We provide the pipeline in the form of deterministic and reproducible code to synthesize the robust output-feedback MPC from data. We empirically demonstrate robust constraint satisfaction and recursive feasibility in quadrotor simulations using Gazebo.

ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning

Human teaching effort is a significant bottleneck for the broader applicability of interactive imitation learning. To reduce the number of required queries, existing methods employ active learning to query the human teacher only in uncertain, risky, or novel situations. However, during these queries, the novice's planned actions are not utilized despite containing valuable information, such as the novice's capabilities, as well as corresponding uncertainty levels. To this end, we allow the novice to say: "I plan to do this, but I am uncertain." We introduce the Active Skill-level Data Aggregation (ASkDAgger) framework, which leverages teacher feedback on the novice plan in three key ways: (1) S-Aware Gating (SAG): Adjusts the gating threshold to track sensitivity, specificity, or a minimum success rate; (2) Foresight Interactive Experience Replay (FIER), which recasts valid and relabeled novice action plans into demonstrations; and (3) Prioritized Interactive Experience Replay (PIER), which prioritizes replay based on uncertainty, novice success, and demonstration age. Together, these components balance query frequency with failure incidence, reduce the number of required demonstration annotations, improve generalization, and speed up adaptation to changing domains. We validate the effectiveness of ASkDAgger through language-conditioned manipulation tasks in both simulation and real-world environments. Code, data, and videos are available at https://askdagger.github.io.

A Step-by-step Guide on Nonlinear Model Predictive Control for Safe Mobile Robot Navigation

Designing a Model Predictive Control (MPC) scheme that enables a mobile robot to safely navigate through an obstacle-filled environment is a complicated yet essential task in robotics. In this technical report, safety refers to ensuring that the robot respects state and input constraints while avoiding collisions with obstacles despite the presence of disturbances and measurement noise. This report offers a step-by-step approach to implementing Nonlinear Model Predictive Control (NMPC) schemes addressing these safety requirements. Numerous books and survey papers provide comprehensive overviews of linear MPC (LMPC) \cite{bemporad2007robust,kouvaritakis2016model}, NMPC \cite{rawlings2017model,allgower2004nonlinear,mayne2014model,grune2017nonlinear,saltik2018outlook}, and their applications in various domains, including robotics \cite{nascimento2018nonholonomic,nguyen2021model,shi2021advanced,wei2022mpc}. This report does not aim to replicate those exhaustive reviews. Instead, it focuses specifically on NMPC as a foundation for safe mobile robot navigation. The goal is to provide a practical and accessible path from theoretical concepts to mathematical proofs and implementation, emphasizing safety and performance guarantees. It is intended for researchers, robotics engineers, and practitioners seeking to bridge the gap between theoretical NMPC formulations and real-world robotic applications. This report is not necessarily meant to remain fixed over time. If someone finds an error in the presented theory, please reach out via the given email addresses. We are happy to update the document if necessary.

A Vehicle System for Navigating Among Vulnerable Road Users Including Remote Operation

We present a vehicle system capable of navigating safely and efficiently around Vulnerable Road Users (VRUs), such as pedestrians and cyclists. The system comprises key modules for environment perception, localization and mapping, motion planning, and control, integrated into a prototype vehicle. A key innovation is a motion planner based on Topology-driven Model Predictive Control (T-MPC). The guidance layer generates multiple trajectories in parallel, each representing a distinct strategy for obstacle avoidance or non-passing. The underlying trajectory optimization constrains the joint probability of collision with VRUs under generic uncertainties. To address extraordinary situations ("edge cases") that go beyond the autonomous capabilities - such as construction zones or encounters with emergency responders - the system includes an option for remote human operation, supported by visual and haptic guidance. In simulation, our motion planner outperforms three baseline approaches in terms of safety and efficiency. We also demonstrate the full system in prototype vehicle tests on a closed track, both in autonomous and remotely operated modes.

EAGERx: Graph-Based Framework for Sim2real Robot Learning

Sim2real, that is, the transfer of learned control policies from simulation to real world, is an area of growing interest in robotics due to its potential to efficiently handle complex tasks. The sim2real approach faces challenges due to mismatches between simulation and reality. These discrepancies arise from inaccuracies in modeling physical phenomena and asynchronous control, among other factors. To this end, we introduce EAGERx, a framework with a unified software pipeline for both real and simulated robot learning. It can support various simulators and aids in integrating state, action and time-scale abstractions to facilitate learning. EAGERx's integrated delay simulation, domain randomization features, and proposed synchronization algorithm contribute to narrowing the sim2real gap. We demonstrate (in the context of robot learning and beyond) the efficacy of EAGERx in accommodating diverse robotic systems and maintaining consistent simulation behavior. EAGERx is open source and its code is available at https://eagerx.readthedocs.io.

Embedded Hierarchical MPC for Autonomous Navigation

To efficiently deploy robotic systems in society, mobile robots need to autonomously and safely move through complex environments. Nonlinear model predictive control (MPC) methods provide a natural way to find a dynamically feasible trajectory through the environment without colliding with nearby obstacles. However, the limited computation power available on typical embedded robotic systems, such as quadrotors, poses a challenge to running MPC in real-time, including its most expensive tasks: constraints generation and optimization. To address this problem, we propose a novel hierarchical MPC scheme that interconnects a planning and a tracking layer. The planner constructs a trajectory with a long prediction horizon at a slow rate, while the tracker ensures trajectory tracking at a relatively fast rate. We prove that the proposed framework avoids collisions and is recursively feasible. Furthermore, we demonstrate its effectiveness in simulations and lab experiments with a quadrotor that needs to reach a goal position in a complex static environment. The code is efficiently implemented on the quadrotor's embedded computer to ensure real-time feasibility. Compared to a state-of-the-art single-layer MPC formulation, this allows us to increase the planning horizon by a factor of 5, which results in significantly better performance.

DART: A Compact Platform For Autonomous Driving Research

This paper presents the design of a research platform for autonomous driving applications, the Delft's Autonomous-driving Robotic Testbed (DART). Our goal was to design a small-scale car-like robot equipped with all the hardware needed for on-board navigation and control while keeping it cost-effective and easy to replicate. To develop DART, we built on an existing off-the-shelf model and augmented its sensor suite to improve its capabilities for control and motion planning tasks. We detail the hardware setup and the system identification challenges to derive the vehicle's models. Furthermore, we present some use cases where we used DART to test different motion planning applications to show the versatility of the platform. Finally, we provide a git repository with all the details to replicate DART, complete with a simulation environment and the data used for system identification.