Luigi Palmieri

Yash Goel, Narunas Vaskevicius, Luigi Palmieri et al.

We investigate the task of object goal navigation in unknown environments where the target is specified by a semantic label (e.g. find a couch). Such a navigation task is especially challenging as it requires understanding of semantic context in diverse settings. Most of the prior work tackles this problem under the assumption of a discrete action policy whereas we present an approach with continuous control which brings it closer to real world applications. We propose a deep neural network architecture and loss function to predict dense cost maps that implicitly contain semantic context and guide the robot towards the semantic goal. We also present a novel way of fusing mid-level visual representations in our architecture to provide additional semantic cues for cost map prediction. The estimated cost maps are then used by a sampling-based model predictive controller (MPC) for generating continuous robot actions. The preliminary experiments suggest that the cost maps generated by our network are suitable for the MPC and can guide the agent to the semantic goal more efficiently than a baseline approach. The results also indicate the importance of mid-level representations for navigation by improving the success rate by 7 percentage points.

Luigi Palmieri, Lorenzo Valerio, Chiara Boldrini et al.

In a decentralized machine learning system, data is typically partitioned among multiple devices or nodes, each of which trains a local model using its own data. These local models are then shared and combined to create a global model that can make accurate predictions on new data. In this paper, we start exploring the role of the network topology connecting nodes on the performance of a Machine Learning model trained through direct collaboration between nodes. We investigate how different types of topologies impact the "spreading of knowledge", i.e., the ability of nodes to incorporate in their local model the knowledge derived by learning patterns in data available in other nodes across the networks. Specifically, we highlight the different roles in this process of more or less connected nodes (hubs and leaves), as well as that of macroscopic network properties (primarily, degree distribution and modularity). Among others, we show that, while it is known that even weak connectivity among network components is sufficient for information spread, it may not be sufficient for knowledge spread. More intuitively, we also find that hubs have a more significant role than leaves in spreading knowledge, although this manifests itself not only for heavy-tailed distributions but also when "hubs" have only moderately more connections than leaves. Finally, we show that tightly knit communities severely hinder knowledge spread.

Luigi Palmieri, Chiara Boldrini, Lorenzo Valerio et al.

Fully decentralized learning enables the distribution of learning resources and decision-making capabilities across multiple user devices or nodes, and is rapidly gaining popularity due to its privacy-preserving and decentralized nature. Importantly, this crowdsourcing of the learning process allows the system to continue functioning even if some nodes are affected or disconnected. In a disaster scenario, communication infrastructure and centralized systems may be disrupted or completely unavailable, hindering the possibility of carrying out standard centralized learning tasks in these settings. Thus, fully decentralized learning can help in this case. However, transitioning from centralized to peer-to-peer communications introduces a dependency between the learning process and the topology of the communication graph among nodes. In a disaster scenario, even peer-to-peer communications are susceptible to abrupt changes, such as devices running out of battery or getting disconnected from others due to their position. In this study, we investigate the effects of various disruptions to peer-to-peer communications on decentralized learning in a disaster setting. We examine the resilience of a decentralized learning process when a subset of devices drop from the process abruptly. To this end, we analyze the difference between losing devices holding data, i.e., potential knowledge, vs. devices contributing only to the graph connectivity, i.e., with no data. Our findings on a Barabasi-Albert graph topology, where training data is distributed across nodes in an IID fashion, indicate that the accuracy of the learning process is more affected by a loss of connectivity than by a loss of data. Nevertheless, the network remains relatively robust, and the learning process can achieve a good level of accuracy.

Utsav Panchal, Yuchen Liu, Luigi Palmieri et al.

Accurately predicting human behaviors is crucial for mobile robots operating in human-populated environments. While prior research primarily focuses on predicting actions in single-human scenarios from an egocentric view, several robotic applications require understanding multiple human behaviors from a third-person perspective. To this end, we present CAMP-VLM (Context-Aware Multi-human behavior Prediction): a Vision Language Model (VLM)-based framework that incorporates contextual features from visual input and spatial awareness from scene graphs to enhance prediction of humans-scene interactions. Due to the lack of suitable datasets for multi-human behavior prediction from an observer view, we perform fine-tuning of CAMP-VLM with synthetic human behavior data generated by a photorealistic simulator, and evaluate the resulting models on both synthetic and real-world sequences to assess their generalization capabilities. Leveraging Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO), CAMP-VLM outperforms the best-performing baseline by up to 66.9% in prediction accuracy.

Dingrui Wang, Hongyuan Ye, Zhihao Liang et al.

While recent world models generate highly realistic videos, their ability to perform robot path planning remains unclear and unquantified. We introduce Target-Bench, the first benchmark specifically designed to evaluate world models on mapless path planning toward semantic targets in real-world environments. Target-Bench provides 450 robot-collected video sequences spanning 45 semantic categories with SLAM-based ground truth trajectories. Our evaluation pipeline recovers camera motion from generated videos and measures planning performance using five complementary metrics that quantify target-reaching capability, trajectory accuracy, and directional consistency. We evaluate state-of-the-art models including Sora 2, Veo 3.1, and the Wan series. The best off-the-shelf model (Wan2.2-Flash) achieves only 0.299 overall score, revealing significant limitations in current world models for robotic planning tasks. We show that fine-tuning an open-source 5B-parameter model on only 325 scenarios from our dataset achieves 0.345 overall score -- an improvement of more than 400% over its base version (0.066) and 15% higher than the best off-the-shelf model. We will open-source the code and dataset.

Eric Heiden, Luigi Palmieri, Kai O. Arras et al.

Planning smooth and energy-efficient motions for wheeled mobile robots is a central task for applications ranging from autonomous driving to service and intralogistic robotics. Over the past decades, a wide variety of motion planners, steer functions and path-improvement techniques have been proposed for such non-holonomic systems. With the objective of comparing this large assortment of state-of-the-art motion-planning techniques, we introduce a novel open-source motion-planning benchmark for wheeled mobile robots, whose scenarios resemble real-world applications (such as navigating warehouses, moving in cluttered cities or parking), and propose metrics for planning efficiency and path quality. Our benchmark is easy to use and extend, and thus allows practitioners and researchers to evaluate new motion-planning algorithms, scenarios and metrics easily. We use our benchmark to highlight the strengths and weaknesses of several common state-of-the-art motion planners and provide recommendations on when they should be used.

Yuchen Liu, Luigi Palmieri, Sebastian Koch et al.

Recent advancements in Large Language Models (LLMs) have sparked a revolution across many research fields. In robotics, the integration of common-sense knowledge from LLMs into task and motion planning has drastically advanced the field by unlocking unprecedented levels of context awareness. Despite their vast collection of knowledge, large language models may generate infeasible plans due to hallucinations or missing domain information. To address these challenges and improve plan feasibility and computational efficiency, we introduce DELTA, a novel LLM-informed task planning approach. By using scene graphs as environment representations within LLMs, DELTA achieves rapid generation of precise planning problem descriptions. To enhance planning performance, DELTA decomposes long-term task goals with LLMs into an autoregressive sequence of sub-goals, enabling automated task planners to efficiently solve complex problems. In our extensive evaluation, we show that DELTA enables an efficient and fully automatic task planning pipeline, achieving higher planning success rates and significantly shorter planning times compared to the state of the art. Project webpage: https://delta-llm.github.io/

Saumya Saxena, Blake Buchanan, Chris Paxton et al.

In Embodied Question Answering (EQA), agents must explore and develop a semantic understanding of an unseen environment to answer a situated question with confidence. This problem remains challenging in robotics, due to the difficulties in obtaining useful semantic representations, updating these representations online, and leveraging prior world knowledge for efficient planning and exploration. To address these limitations, we propose GraphEQA, a novel approach that utilizes real-time 3D metric-semantic scene graphs (3DSGs) and task relevant images as multi-modal memory for grounding Vision-Language Models (VLMs) to perform EQA tasks in unseen environments. We employ a hierarchical planning approach that exploits the hierarchical nature of 3DSGs for structured planning and semantics-guided exploration. We evaluate GraphEQA in simulation on two benchmark datasets, HM-EQA and OpenEQA, and demonstrate that it outperforms key baselines by completing EQA tasks with higher success rates and fewer planning steps. We further demonstrate GraphEQA in multiple real-world home and office environments.

Luigi Palmieri, Chiara Boldrini, Lorenzo Valerio et al.

Fully decentralized learning is gaining momentum for training AI models at the Internet's edge, addressing infrastructure challenges and privacy concerns. In a decentralized machine learning system, data is distributed across multiple nodes, with each node training a local model based on its respective dataset. The local models are then shared and combined to form a global model capable of making accurate predictions on new data. Our exploration focuses on how different types of network structures influence the spreading of knowledge - the process by which nodes incorporate insights gained from learning patterns in data available on other nodes across the network. Specifically, this study investigates the intricate interplay between network structure and learning performance using three network topologies and six data distribution methods. These methods consider different vertex properties, including degree centrality, betweenness centrality, and clustering coefficient, along with whether nodes exhibit high or low values of these metrics. Our findings underscore the significance of global centrality metrics (degree, betweenness) in correlating with learning performance, while local clustering proves less predictive. We highlight the challenges in transferring knowledge from peripheral to central nodes, attributed to a dilution effect during model aggregation. Additionally, we observe that central nodes exert a pull effect, facilitating the spread of knowledge. In examining degree distribution, hubs in Barabasi-Albert networks positively impact learning for central nodes but exacerbate dilution when knowledge originates from peripheral nodes. Finally, we demonstrate the formidable challenge of knowledge circulation outside of segregated communities.

Moritz Schneider, Robert Krug, Narunas Vaskevicius et al.

Visual Reinforcement Learning (RL) methods often require extensive amounts of data. As opposed to model-free RL, model-based RL (MBRL) offers a potential solution with efficient data utilization through planning. Additionally, RL lacks generalization capabilities for real-world tasks. Prior work has shown that incorporating pre-trained visual representations (PVRs) enhances sample efficiency and generalization. While PVRs have been extensively studied in the context of model-free RL, their potential in MBRL remains largely unexplored. In this paper, we benchmark a set of PVRs on challenging control tasks in a model-based RL setting. We investigate the data efficiency, generalization capabilities, and the impact of different properties of PVRs on the performance of model-based agents. Our results, perhaps surprisingly, reveal that for MBRL current PVRs are not more sample efficient than learning representations from scratch, and that they do not generalize better to out-of-distribution (OOD) settings. To explain this, we analyze the quality of the trained dynamics model. Furthermore, we show that data diversity and network architecture are the most important contributors to OOD generalization performance.

Yuchen Liu, Lino Lerch, Luigi Palmieri et al.

Predicting human behavior in shared environments is crucial for safe and efficient human-robot interaction. Traditional data-driven methods to that end are pre-trained on domain-specific datasets, activity types, and prediction horizons. In contrast, the recent breakthroughs in Large Language Models (LLMs) promise open-ended cross-domain generalization to describe various human activities and make predictions in any context. In particular, Multimodal LLMs (MLLMs) are able to integrate information from various sources, achieving more contextual awareness and improved scene understanding. The difficulty in applying general-purpose MLLMs directly for prediction stems from their limited capacity for processing large input sequences, sensitivity to prompt design, and expensive fine-tuning. In this paper, we present a systematic analysis of applying pre-trained MLLMs for context-aware human behavior prediction. To this end, we introduce a modular multimodal human activity prediction framework that allows us to benchmark various MLLMs, input variations, In-Context Learning (ICL), and autoregressive techniques. Our evaluation indicates that the best-performing framework configuration is able to reach 92.8% semantic similarity and 66.1% exact label accuracy in predicting human behaviors in the target frame.

Luigi Palmieri, Chiara Boldrini, Lorenzo Valerio et al.

In the vibrant landscape of AI research, decentralised learning is gaining momentum. Decentralised learning allows individual nodes to keep data locally where they are generated and to share knowledge extracted from local data among themselves through an interactive process of collaborative refinement. This paradigm supports scenarios where data cannot leave local nodes due to privacy or sovereignty reasons or real-time constraints imposing proximity of models to locations where inference has to be carried out. The distributed nature of decentralised learning implies significant new research challenges with respect to centralised learning. Among them, in this paper, we focus on robustness issues. Specifically, we study the effect of nodes' disruption on the collective learning process. Assuming a given percentage of "central" nodes disappear from the network, we focus on different cases, characterised by (i) different distributions of data across nodes and (ii) different times when disruption occurs with respect to the start of the collaborative learning task. Through these configurations, we are able to show the non-trivial interplay between the properties of the network connecting nodes, the persistence of knowledge acquired collectively before disruption or lack thereof, and the effect of data availability pre- and post-disruption. Our results show that decentralised learning processes are remarkably robust to network disruption. As long as even minimum amounts of data remain available somewhere in the network, the learning process is able to recover from disruptions and achieve significant classification accuracy. This clearly varies depending on the remaining connectivity after disruption, but we show that even nodes that remain completely isolated can retain significant knowledge acquired before the disruption.

Lukas Heuer, Yufei Zhu, Luigi Palmieri et al.

Deploying multi-robot systems in environments shared with dynamic and uncontrollable agents presents significant challenges, especially for large robot fleets. In such environments, individual robot operations can be delayed due to unforeseen conflicts with uncontrollable agents. While existing research primarily focuses on preserving the completeness of Multi-Agent Path Finding (MAPF) solutions considering delays, there is limited emphasis on utilizing additional environmental information to enhance solution quality in the presence of other dynamic agents. To this end, we propose Flow-Aware Multi-Agent Path Finding (FA-MAPF), a novel framework that integrates learned motion patterns of uncontrollable agents into centralized MAPF algorithms. Our evaluation, conducted on a diverse set of benchmark maps with simulated uncontrollable agents and on a real-world map with recorded human trajectories, demonstrates the effectiveness of FA-MAPF compared to state-of-the-art baselines. The experimental results show that FA-MAPF can consistently reduce conflicts with uncontrollable agents, up to 55%, without compromising task efficiency.

Moritz Schneider, Robert Krug, Narunas Vaskevicius et al.

Empowerment, an information-theoretic measure of an agent's potential influence on its environment, has emerged as a powerful intrinsic motivation and exploration framework for reinforcement learning (RL). Besides for unsupervised RL and skill learning algorithms, the specific use of empowerment as a pre-training signal has received limited attention in the literature. We show that empowerment can be used as a pre-training signal for data-efficient downstream task adaptation. For this we extend the traditional notion of empowerment by introducing discounted empowerment, which balances the agent's control over the environment across short- and long-term horizons. Leveraging this formulation, we propose a novel pre-training paradigm that initializes policies to maximize discounted empowerment, enabling agents to acquire a robust understanding of environmental dynamics. We analyze empowerment-based pre-training for various existing RL algorithms and empirically demonstrate its potential as a general-purpose initialization strategy: empowerment-maximizing policies with long horizons are data-efficient and effective, leading to improved adaptability in downstream tasks. Our findings pave the way for future research to scale this framework to high-dimensional and complex tasks, further advancing the field of RL.

Yu Yao, Salil Bhatnagar, Markus Mazzola et al.

Rare, yet critical, scenarios pose a significant challenge in testing and evaluating autonomous driving planners. Relying solely on real-world driving scenes requires collecting massive datasets to capture these scenarios. While automatic generation of traffic scenarios appears promising, data-driven models require extensive training data and often lack fine-grained control over the output. Moreover, generating novel scenarios from scratch can introduce a distributional shift from the original training scenes which undermines the validity of evaluations especially for learning-based planners. To sidestep this, recent work proposes to generate challenging scenarios by augmenting original scenarios from the test set. However, this involves the manual augmentation of scenarios by domain experts. An approach that is unable to meet the demands for scale in the evaluation of self-driving systems. Therefore, this paper introduces a novel LLM-agent based framework for augmenting real-world traffic scenarios using natural language descriptions, addressing the limitations of existing methods. A key innovation is the use of an agentic design, enabling fine-grained control over the output and maintaining high performance even with smaller, cost-effective LLMs. Extensive human expert evaluation demonstrates our framework's ability to accurately adhere to user intent, generating high quality augmented scenarios comparable to those created manually.

Andrey Rudenko, Luigi Palmieri, Johannes Doellinger et al.

Understanding and anticipating human activity is an important capability for intelligent systems in mobile robotics, autonomous driving, and video surveillance. While learning from demonstrations with on-site collected trajectory data is a powerful approach to discover recurrent motion patterns, generalization to new environments, where sufficient motion data are not readily available, remains a challenge. In many cases, however, semantic information about the environment is a highly informative cue for the prediction of pedestrian motion or the estimation of collision risks. In this work, we infer occupancy priors of human motion using only semantic environment information as input. To this end we apply and discuss a traditional Inverse Optimal Control approach, and propose a novel one based on Convolutional Neural Networks (CNN) to predict future occupancy maps. Our CNN method produces flexible context-aware occupancy estimations for semantically uniform map regions and generalizes well already with small amounts of training data. Evaluated on synthetic and real-world data, it shows superior results compared to several baselines, marking a qualitative step-up in semantic environment assessment.

Alexander Berndt, Niels Van Duijkeren, Luigi Palmieri et al.

In this paper we consider multiple Automated Guided Vehicles (AGVs) navigating a common workspace to fulfill various intralogistics tasks, typically formulated as the Multi-Agent Path Finding (MAPF) problem. To keep plan execution deadlock-free, one approach is to construct an Action Dependency Graph (ADG) which encodes the ordering of AGVs as they proceed along their routes. Using this method, delayed AGVs occasionally require others to wait for them at intersections, thereby affecting the plan execution efficiency. If the workspace is shared by dynamic obstacles such as humans or third party robots, AGVs can experience large delays. A common mitigation approach is to re-solve the MAPF using the current, delayed AGV positions. However, solving the MAPF is time-consuming, making this approach inefficient, especially for large AGV teams. In this work, we present an online method to repeatedly modify a given acyclic ADG to minimize route completion times of each AGV. Our approach persistently maintains an acyclic ADG, necessary for deadlock-free plan execution. We evaluate the approach by considering simulations with random disturbances on the execution and show faster route completion times compared to the baseline ADG-based execution management approach.

Tobias Schoels, Per Rutquist, Luigi Palmieri et al.

Robots have been operating in dynamic environments and shared workspaces for decades. Most optimization based motion planning methods, however, do not consider the movement of other agents, e.g. humans or other robots, and therefore do not guarantee collision avoidance in such scenarios. This paper builds upon the Convex Inner ApprOximation (CIAO) method and proposes a motion planning algorithm that guarantees collision avoidance in predictable dynamic environments. Furthermore, it generalizes CIAO's free region concept to arbitrary norms and proposes a cost function to approximate time optimal motion planning. The proposed method, CIAO$^\star$, finds kinodynamically feasible and collision free trajectories for constrained single body robots using model predictive control (MPC). It optimizes the motion of one agent and accounts for the predicted movement of surrounding agents and obstacles. The experimental evaluation shows that CIAO$^\star$ reaches close to time optimal behavior.

Luigi Palmieri, Leonard Bruns, Michael Meurer et al.

A key challenge in robotics is the efficient generation of optimal robot motion with safety guarantees in cluttered environments. Recently, deterministic optimal sampling-based motion planners have been shown to achieve good performance towards this end, in particular in terms of planning efficiency, final solution cost, quality guarantees as well as non-probabilistic completeness. Yet their application is still limited to relatively simple systems (i.e., linear, holonomic, Euclidean state spaces). In this work, we extend this technique to the class of symmetric and optimal driftless systems by presenting Dispertio, an offline dispersion optimization technique for computing sampling sets, aware of differential constraints, for sampling-based robot motion planning. We prove that the approach, when combined with PRM*, is deterministically complete and retains asymptotic optimality. Furthermore, in our experiments we show that the proposed deterministic sampling technique outperforms several baselines and alternative methods in terms of planning efficiency and solution cost.

Tobias Schoels, Luigi Palmieri, Kai O. Arras et al.

Even though mobile robots have been around for decades, trajectory optimization and continuous time collision avoidance remain subject of active research. Existing methods trade off between path quality, computational complexity, and kinodynamic feasibility. This work approaches the problem using a nonlinear model predictive control (NMPC) framework, that is based on a novel convex inner approximation of the collision avoidance constraint. The proposed Convex Inner ApprOximation (CIAO) method finds kinodynamically feasible and continuous time collision free trajectories, in few iterations, typically one. For a feasible initialization, the approach is guaranteed to find a feasible solution, i.e. it preserves feasibility. Our experimental evaluation shows that CIAO outperforms state of the art baselines in terms of planning efficiency and path quality. Experiments on a robot with 12 states show that it also scales to high-dimensional systems. Furthermore real-world experiments demonstrate its capability of unifying trajectory optimization and tracking for safe motion planning in dynamic environments.

Andrey Rudenko, Luigi Palmieri, Michael Herman et al.

With growing numbers of intelligent autonomous systems in human environments, the ability of such systems to perceive, understand and anticipate human behavior becomes increasingly important. Specifically, predicting future positions of dynamic agents and planning considering such predictions are key tasks for self-driving vehicles, service robots and advanced surveillance systems. This paper provides a survey of human motion trajectory prediction. We review, analyze and structure a large selection of work from different communities and propose a taxonomy that categorizes existing methods based on the motion modeling approach and level of contextual information used. We provide an overview of the existing datasets and performance metrics. We discuss limitations of the state of the art and outline directions for further research.

Luigi Palmieri, Andrey Rudenko, Kai O. Arras

We introduce and show preliminary results of a fast randomized method that finds a set of K paths lying in distinct homotopy classes. We frame the path planning task as a graph search problem, where the navigation graph is based on a Voronoi diagram. The search is biased by a cost function derived from the social force model that is used to generate and select the paths. We compare our method to Yen's algorithm, and empirically show that our approach is faster to find a subset of homotopy classes. Furthermore our approach computes a set of more diverse paths with respect to the baseline while obtaining a negligible loss in path quality.

Luigi Palmieri

A reactive obstacle avoidance method for mobile manipulators is presented. The objectives of the developed algorithm are twofold. The first one is to find a trajectory in the configuration space of a mobile manipulator so as to follow a given trajectory in the task space. The second objective consists in locally adjusting the trajectory in the configuration space in order to avoid collisions with potentially moving obstacles and self-collisions in unstructured and dynamic environments. The perception is exclusively based on a set of proximity sensors distributed on the robot mechanical structure and visual information are not required. Thanks to the adoption of this kind of proximity distributed perception, the approach does not require a 3D model of the robot and allows the real-time collision avoidance without the need of a sensorized environment. To achieve the features cited above, a behaviour-based technique known as Null-Space-Based (NSB) approach has been adopted with some modifications.On one hand, the concept of a total pseudo-energy based on the information from the distributed sensors has been introduced. On the other hand, a method to combine different tasks has been proposed to guarantee the smoothness of the realtime trajectory adjustments. Another significant feature of the method is the strict coordination between the base and the arm exploiting the redundant degrees of freedom, that is a relevant topic in mobile manipulation.