arXiv subjects

Ioannis Karamouzas

Publications and source records attributed to Ioannis Karamouzas.

14 recordsLinked to original sources

arXiv2026

Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review

With the emergence of powerful data-driven methods in human trajectory prediction (HTP), gaining a finer understanding of multi-agent interactions lies within hand's reach, with important implications in areas such as social robot navigation, autonomous driving, and crowd modeling. This survey reviews some of the most recent advancements in deep learning-based multi-agent trajectory prediction, focusing on studies published between 2020 and 2025. We categorize the existing methods based on their architectural design, their input representations, and their overall prediction strategies, placing a particular emphasis on models evaluated using the ETH/UCY benchmark. Furthermore, we highlight key challenges and future research directions in the field of multi-agent HTP.

cs.CV↗

arXiv2026

Gen-C: Populating Virtual Worlds with Generative Crowds

Over the past two decades, researchers have made significant steps in simulating agent-based human crowds, yet most efforts remain focused on low-level tasks such as collision avoidance, path following, and flocking. As a result, these approaches often struggle to capture the high-level behaviors that emerge from sustained agent-agent and agent-environment interactions over time. We introduce Generative Crowds (Gen-C), a generative framework that produces crowd scenarios capturing agent-agent and agent-environment interactions, shaping coherent high-level crowd plans. To avoid the labor-intensive process of collecting and annotating real crowd video data, we leverage Large Language Models (LLMs) to bootstrap synthetic datasets of crowd scenarios. To represent those scenarios, we propose a time-expanded graph structure encoding actions, interactions, and spatial context. Gen-C employs a dual Variational Graph Autoencoder (VGAE) architecture that jointly learns connectivity patterns and node features conditioned on textual and structural signals, overcoming the limitations of direct LLM generation to enable scalable, environment-aware multi-agent crowd simulations. We demonstrate the effectiveness of our framework on scenarios with diverse behaviors such as a University Campus and a Train Station, showing that it generates heterogeneous crowds, coherent interactions, and high-level decision-making patterns consistent with the provided context.

cs.GR↗

arXiv2025

Learning to Ball: Composing Policies for Long-Horizon Basketball Moves

Learning a control policy for a multi-phase, long-horizon task, such as basketball maneuvers, remains challenging for reinforcement learning approaches due to the need for seamless policy composition and transitions between skills. A long-horizon task typically consists of distinct subtasks with well-defined goals, separated by transitional subtasks with unclear goals but critical to the success of the entire task. Existing methods like the mixture of experts and skill chaining struggle with tasks where individual policies do not share significant commonly explored states or lack well-defined initial and terminal states between different phases. In this paper, we introduce a novel policy integration framework to enable the composition of drastically different motor skills in multi-phase long-horizon tasks with ill-defined intermediate states. Based on that, we further introduce a high-level soft router to enable seamless and robust transitions between the subtasks. We evaluate our framework on a set of fundamental basketball skills and challenging transitions. Policies trained by our approach can effectively control the simulated character to interact with the ball and accomplish the long-horizon task specified by real-time user commands, without relying on ball trajectory references.

cs.GR↗

arXiv2023

A Study in Zucker: Insights on Interactions Between Humans and Small Service Robots

Despite recent advancements in human-robot interaction (HRI), there is still limited knowledge about how humans interact and behave in the presence of small service indoor robots and, subsequently, about the human-centered behavior of such robots. This also raises concerns about the applicability of current trajectory prediction methods to indoor HRI settings as well as the accuracy of existing crowd simulation models in shared environments. To address these issues, we introduce a new HRI dataset focusing on interactions between humans and small differential drive robots running different types of controllers. Our analysis shows that anticipatory and non-anticipatory robot controllers impose similar constraints to humans' safety and efficiency. Additionally, we found that current state-of-the-art models for human trajectory prediction can adequately extend to indoor HRI settings. Finally, we show that humans respond differently to small differential drives than to other humans when collisions are imminent, since interacting with small robots can only cause a finite level of social discomfort as compared to human-human interactions. Our dataset and related code and models are available at: https://motion-lab.github.io/ZuckerDataset.

cs.RO↗

arXiv2023

AdaptNet: Policy Adaptation for Physics-Based Character Control

Motivated by humans' ability to adapt skills in the learning of new ones, this paper presents AdaptNet, an approach for modifying the latent space of existing policies to allow new behaviors to be quickly learned from like tasks in comparison to learning from scratch. Building on top of a given reinforcement learning controller, AdaptNet uses a two-tier hierarchy that augments the original state embedding to support modest changes in a behavior and further modifies the policy network layers to make more substantive changes. The technique is shown to be effective for adapting existing physics-based controllers to a wide range of new styles for locomotion, new task targets, changes in character morphology and extensive changes in environment. Furthermore, it exhibits significant increase in learning efficiency, as indicated by greatly reduced training times when compared to training from scratch or using other approaches that modify existing policies. Code is available at https://motion-lab.github.io/AdaptNet.

cs.GR↗

arXiv2023

Human-Inspired Multi-Agent Navigation using Knowledge Distillation

Despite significant advancements in the field of multi-agent navigation, agents still lack the sophistication and intelligence that humans exhibit in multi-agent settings. In this paper, we propose a framework for learning a human-like general collision avoidance policy for agent-agent interactions in fully decentralized, multi-agent environments. Our approach uses knowledge distillation with reinforcement learning to shape the reward function based on expert policies extracted from human trajectory demonstrations through behavior cloning. We show that agents trained with our approach can take human-like trajectories in collision avoidance and goal-directed steering tasks not provided by the demonstrations, outperforming the experts as well as learning-based agents trained without knowledge distillation.

cs.RO↗

arXiv2023

Context-Aware Timewise VAEs for Real-Time Vehicle Trajectory Prediction

Real-time, accurate prediction of human steering behaviors has wide applications, from developing intelligent traffic systems to deploying autonomous driving systems in both real and simulated worlds. In this paper, we present ContextVAE, a context-aware approach for multi-modal vehicle trajectory prediction. Built upon the backbone architecture of a timewise variational autoencoder, ContextVAE observation encoding employs a dual attention mechanism that accounts for the environmental context and the dynamic agents' states, in a unified way. By utilizing features extracted from semantic maps during agent state encoding, our approach takes into account both the social features exhibited by agents on the scene and the physical environment constraints to generate map-compliant and socially-aware trajectories. We perform extensive testing on the nuScenes prediction challenge, Lyft Level 5 dataset and Waymo Open Motion Dataset to show the effectiveness of our approach and its state-of-the-art performance. In all tested datasets, ContextVAE models are fast to train and provide high-quality multi-modal predictions in real-time. Our code is available at: https://github.com/xupei0610/ContextVAE.

cs.CV↗

arXiv2023

Composite Motion Learning with Task Control

We present a deep learning method for composite and task-driven motion control for physically simulated characters. In contrast to existing data-driven approaches using reinforcement learning that imitate full-body motions, we learn decoupled motions for specific body parts from multiple reference motions simultaneously and directly by leveraging the use of multiple discriminators in a GAN-like setup. In this process, there is no need of any manual work to produce composite reference motions for learning. Instead, the control policy explores by itself how the composite motions can be combined automatically. We further account for multiple task-specific rewards and train a single, multi-objective control policy. To this end, we propose a novel framework for multi-objective learning that adaptively balances the learning of disparate motions from multiple sources and multiple goal-directed control objectives. In addition, as composite motions are typically augmentations of simpler behaviors, we introduce a sample-efficient method for training composite control policies in an incremental manner, where we reuse a pre-trained policy as the meta policy and train a cooperative policy that adapts the meta one for new composite tasks. We show the applicability of our approach on a variety of challenging multi-objective tasks involving both composite motion imitation and multiple goal-directed control.

cs.GR↗

arXiv2022

SocialVAE: Human Trajectory Prediction using Timewise Latents

Predicting pedestrian movement is critical for human behavior analysis and also for safe and efficient human-agent interactions. However, despite significant advancements, it is still challenging for existing approaches to capture the uncertainty and multimodality of human navigation decision making. In this paper, we propose SocialVAE, a novel approach for human trajectory prediction. The core of SocialVAE is a timewise variational autoencoder architecture that exploits stochastic recurrent neural networks to perform prediction, combined with a social attention mechanism and a backward posterior approximation to allow for better extraction of pedestrian navigation strategies. We show that SocialVAE improves current state-of-the-art performance on several pedestrian trajectory prediction benchmarks, including the ETH/UCY benchmark, Stanford Drone Dataset, and SportVU NBA movement dataset. Code is available at: https://github.com/xupei0610/SocialVAE.

cs.CV↗

arXiv2021

A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Control

We present a simple and intuitive approach for interactive control of physically simulated characters. Our work builds upon generative adversarial networks (GAN) and reinforcement learning, and introduces an imitation learning framework where an ensemble of classifiers and an imitation policy are trained in tandem given pre-processed reference clips. The classifiers are trained to discriminate the reference motion from the motion generated by the imitation policy, while the policy is rewarded for fooling the discriminators. Using our GAN-based approach, multiple motor control policies can be trained separately to imitate different behaviors. In runtime, our system can respond to external control signal provided by the user and interactively switch between different policies. Compared to existing methods, our proposed approach has the following attractive properties: 1) achieves state-of-the-art imitation performance without manually designing and fine tuning a reward function; 2) directly controls the character without having to track any target reference pose explicitly or implicitly through a phase state; and 3) supports interactive policy switching without requiring any motion generation or motion matching mechanism. We highlight the applicability of our approach in a range of imitation and interactive control tasks, while also demonstrating its ability to withstand external perturbations as well as to recover balance. Overall, our approach generates high-fidelity motion, has low runtime cost, and can be easily integrated into interactive applications and games.

cs.GR↗

arXiv2021

PFPN: Continuous Control of Physically Simulated Characters using Particle Filtering Policy Network

Data-driven methods for physics-based character control using reinforcement learning have been successfully applied to generate high-quality motions. However, existing approaches typically rely on Gaussian distributions to represent the action policy, which can prematurely commit to suboptimal actions when solving high-dimensional continuous control problems for highly-articulated characters. In this paper, to improve the learning performance of physics-based character controllers, we propose a framework that considers a particle-based action policy as a substitute for Gaussian policies. We exploit particle filtering to dynamically explore and discretize the action space, and track the posterior policy represented as a mixture distribution. The resulting policy can replace the unimodal Gaussian policy which has been the staple for character control problems, without changing the underlying model architecture of the reinforcement learning algorithm used to perform policy optimization. We demonstrate the applicability of our approach on various motion capture imitation tasks. Baselines using our particle-based policies achieve better imitation performance and speed of convergence as compared to corresponding implementations using Gaussians, and are more robust to external perturbations during character control. Related code is available at: https://motion-lab.github.io/PFPN.

cs.LG↗

arXiv2019

NH-TTC: A gradient-based framework for generalized anticipatory collision avoidance

We propose NH-TTC, a general method for fast, anticipatory collision avoidance for autonomous robots having arbitrary equations of motions. Our proposed approach exploits implicit differentiation and subgradient descent to locally optimize the non-convex and non-smooth cost functions that arise from planning over the anticipated future positions of nearby obstacles. The result is a flexible framework capable of supporting high-quality, collision-free navigation with a wide variety of robot motion models in various challenging scenarios. We show results for different navigating tasks, with our method controlling various numbers of agents (with and without reciprocity), on both physical differential drive robots, and simulated robots with different motion models and kinematic and dynamic constraints, including acceleration-controlled agents, differential-drive agents, and smooth car-like agents. The resulting paths are high quality and collision-free, while needing only a few milliseconds of computation as part of an integrated sense-plan-act navigation loop.

cs.RO↗

arXiv2017

ALAN: Adaptive Learning for Multi-Agent Navigation

In multi-agent navigation, agents need to move towards their goal locations while avoiding collisions with other agents and static obstacles, often without communication with each other. Existing methods compute motions that are optimal locally but do not account for the aggregated motions of all agents, producing inefficient global behavior especially when agents move in a crowded space. In this work, we develop methods to allow agents to dynamically adapt their behavior to their local conditions. We accomplish this by formulating the multi-agent navigation problem as an action-selection problem, and propose an approach, ALAN, that allows agents to compute time-efficient and collision-free motions. ALAN is highly scalable because each agent makes its own decisions on how to move using a set of velocities optimized for a variety of navigation tasks. Experimental results show that the agents using ALAN, in general, reach their destinations faster than using ORCA, a state-of-the-art collision avoidance framework, the Social Forces model for pedestrian navigation, and a Predictive collision avoidance model.

cs.MA↗

arXiv2014

Universal power law governing pedestrian interactions

Human crowds often bear a striking resemblance to interacting particle systems, and this has prompted many researchers to describe pedestrian dynamics in terms of interaction forces and potential energies. The correct quantitative form of this interaction, however, has remained an open question. Here, we introduce a novel statistical-mechanical approach to directly measure the interaction energy between pedestrians. This analysis, when applied to a large collection of human motion data, reveals a simple power law interaction that is based not on the physical separation between pedestrians but on their projected time to a potential future collision, and is therefore fundamentally anticipatory in nature. Remarkably, this simple law is able to describe human interactions across a wide variety of situations, speeds and densities. We further show, through simulations, that the interaction law we identify is sufficient to reproduce many known crowd phenomena.

physics.soc-ph↗