Videos are often used to learn or extract the necessary information to complete tasks in ways different than what text or static imagery can provide. However, many existing agent benchmarks neglect long-context video understanding, instead focus- ing on text or static image inputs. To bridge this gap, we introduce VideoWebArena (VideoWA), a benchmark for evaluating the capabilities of long-context multimodal agents for video understanding. VideoWA consists of 2,021 web agent tasks based on manually crafted video tutorials, which total almost four hours of content. For our benchmark, we define a taxonomy of long-context video-based agent tasks with two main areas of focus: skill retention and factual retention. While skill retention tasks evaluate whether an agent can use a given human demonstration to complete a task efficiently, the factual retention task evaluates whether an agent can retrieve instruction-relevant information from a video to complete a task. We find that the best model achieves a 13.3% success rate on factual retention tasks and 45.8% on factual retention QA pairs—far below human success rates of 73.9% and 79.3%, respectively. On skill retention tasks, long-context models perform worse with tutorials than without, exhibiting a 5% performance decrease in WebArena tasks and a 10.3% decrease in VisualWebArena tasks. Our work highlights performance gaps in the agentic abilities of long-context multimodal models and provides as a testbed for the future development of long-context video agents.

Large language models (LLMs) show potential as computer agents, enhancing productivity and software accessibility in multi-modal tasks. However, measuring agent performance in sufficiently realistic and complex environments becomes increasingly challenging as: (i) most benchmarks are limited to specific modalities/domains (e.g., text-only, web navigation, Q&A) and (ii) full benchmark evaluations are slow (on order of magnitude of multiple hours/days) given the multi-step sequential nature of tasks. To address these challenges, we introduce Windows Agent Arena: a general environment focusing exclusively on the Windows operating system (OS) where agents can operate freely within a real OS to use the same applications and tools available to human users when performing tasks. We create 150+ diverse tasks across representative domains that require agentic abilities in planning, screen understanding, and tool usage. Our benchmark is scalable and can be seamlessly parallelized for a full benchmark evaluation in as little as $20$ minutes. Our work not only speeds up the development and evaluation cycle of multi-modal agents, but also highlights and analyzes existing shortfalls in the agentic abilities of several multimodal LLMs as agents within the Windows computing environment---with the best achieving only a 19.5\% success rate compared to a human success rate of 74.5\%.

Large-scale self-supervised models have recently revolutionized our ability to perform a variety of tasks within the vision and language domains. However, using such models for autonomous systems is challenging because of safety requirements: besides executing correct actions, an autonomous agent must also avoid the high cost and potentially fatal critical mistakes. Traditionally, self-supervised training mainly focuses on imitating previously observed behaviors, and the training demonstrations carry no notion of which behaviors should be explicitly avoided. In this work, we propose Control Barrier Transformer (ConBaT), an approach that learns safe behaviors from demonstrations in a self-supervised fashion. ConBaT is inspired by the concept of control barrier functions in control theory and uses a causal transformer that learns to predict safe robot actions autoregressively using a critic that requires minimal safety data labeling. During deployment, we employ a lightweight online optimization to find actions that ensure future states lie within the learned safe set. We apply our approach to different simulated control tasks and show that our method results in safer control policies compared to other classical and learning-based methods such as imitation learning, reinforcement learning, and model predictive control.

We present EvDNeRF, a pipeline for generating event data and training an event-based dynamic NeRF, for the purpose of faithfully reconstructing eventstreams on scenes with rigid and non-rigid deformations that may be too fast to capture with a standard camera. Event cameras register asynchronous per-pixel brightness changes at MHz rates with high dynamic range, making them ideal for observing fast motion with almost no motion blur. Neural radiance fields (NeRFs) offer visual-quality geometric-based learnable rendering, but prior work with events has only considered reconstruction of static scenes. Our EvDNeRF can predict eventstreams of dynamic scenes from a static or moving viewpoint between any desired timestamps, thereby allowing it to be used as an event-based simulator for a given scene. We show that by training on varied batch sizes of events, we can improve test-time predictions of events at fine time resolutions, outperforming baselines that pair standard dynamic NeRFs with event generators. We release our simulated and real datasets, as well as code for multi-view event-based data generation and the training and evaluation of EvDNeRF models1.

We introduce DualMind, a generalist agent designed to tackle various decision-making tasks that addresses challenges posed by current methods, such as overfitting behaviors and dependence on task-specific fine-tuning. DualMind uses a novel "Dual-phase" training strategy that emulates how humans learn to act in the world. The model first learns fundamental common knowledge through a self-supervised objective tailored for control tasks and then learns how to make decisions based on different contexts through imitating behaviors conditioned on given prompts. DualMind can handle tasks across domains, scenes, and embodiments using just a single set of model weights and can execute zero-shot prompting without requiring task-specific finetuning. We evaluate DualMind on MetaWorld [40] and Habitat [31] through extensive experiments and demonstrate its superior generalizability compared to previous techniques, outperforming other generalist agents by over 50% and 70% on Habitat and MetaWorld, respectively. On the 45 tasks in MetaWorld, DualMind achieves over 30 tasks at a 90% success rate. Our source code is available at https://github.com/yunyikristy/DualMind.

Natural language is one of the most intuitive ways to express human intent. However, translating instructions and commands towards robotic motion generation and deployment in the real world is far from being an easy task. The challenge of combining a robot's inherent low-level geometric and kinodynamic constraints with a human's high-level semantic instructions traditionally is solved using task-specific solutions with little generalizability between hardware platforms, often with the use of static sets of target actions and commands. This work instead proposes a flexible language-based framework that allows a user to modify generic robotic trajectories. Our method leverages pre-trained language models (BERT and CLIP) to encode the user's intent and target objects directly from a free-form text input and scene images, fuses geometrical features generated by a transformer encoder network, and finally outputs trajectories using a transformer decoder, without the need of priors related to the task or robot information. We significantly extend our own previous work presented in [1] by expanding the trajectory parametrization space to 3D and velocity as opposed to just XY movements. In addition, we now train the model to use actual images of the objects in the scene for context (as opposed to textual descriptions), and we evaluate the system in a diverse set of scenarios beyond manipulation, such as aerial and legged robots. Our simulated and real-life experiments demonstrate that our transformer model can successfully follow human intent, modifying the shape and speed of trajectories within multiple environments. Codebase avail-able at: https://github.com/arthurfenderbucker/LaTTe-Language-Trajectory-TransformEr.git.

Robotics has long been a field riddled with complex systems architectures whose modules and connections, whether traditional or learning-based, require significant human expertise and prior knowledge. Inspired by large pre-trained language models, this work introduces a paradigm for pretraining a general purpose representation that can serve as a starting point for multiple tasks on a given robot. We present the Perception-Action Causal Transformer (PACT), a generative transformer-based architecture that aims to build representations directly from robot data in a self-supervised fashion. Through autoregressive prediction of states and actions over time, our model implicitly encodes dynamics and behaviors for a particular robot. Our experimental evaluation focuses on the domain of mobile agents, where we show that this robot-specific representation can function as a single starting point to achieve distinct tasks such as safe navigation, localization and mapping. We evaluate two form factors: a wheeled robot that uses a LiDAR sensor as perception input (MuSHR), and a simulated agent that uses first-person RGB images (Habitat). We show that finetuning small task-specific networks on top of the larger pretrained model results in significantly better performance compared to training a single model from scratch for all tasks simultaneously, and comparable performance to training a separate large model for each task independently. By sharing a common good-quality representation across tasks we can lower overall model capacity and speed up the real-time deployment of such systems.

Natural language is the most intuitive medium for us to interact with other people when expressing commands and instructions. However, using language is seldom an easy task when humans need to express their intent towards robots, since most of the current language interfaces require rigid templates with a static set of action targets and commands. In this work, we provide a flexible language-based interface for human-robot collaboration, which allows a user to reshape existing trajectories for an autonomous agent. We take advantage of recent advancements in the field of large language models (BERT and CLIP) to encode the user command, and then combine these features with trajectory information using multi-modal attention transformers. We train the model using imitation learning over a dataset containing robot trajectories modified by language commands, and treat the trajectory generation process as a sequence prediction problem, analogously to how language generation architectures operate. We evaluate the system in multiple simulated trajectory scenarios, and show a significant performance increase of our model over baseline approaches. In addition, our real-world experiments with a robot arm show that users significantly prefer our natural language interface over traditional methods such as kinesthetic teaching or cost-function programming. Our study shows how the field of robotics can take advantage of large pre-trained language models towards creating more intuitive interfaces between robots and machines. Project webpage: https://arthurfenderbucker.github.io/NL_trajectory_reshaper/

Aerial vehicles are revolutionizing the way filmmakers can capture shots of actors by composing novel aerial and dynamic viewpoints. However, despite great advancements in autonomous flight technology, generating expressive camera behaviors is still a challenge and requires non-technical users to edit a large number of unintuitive control parameters. In this work, we develop a data-driven framework that enables editing of these complex camera positioning parameters in a semantic space (e.g. calm, enjoyable, establishing). First, we generate a database of video clips with a diverse range of shots in a photo-realistic simulator, and use hundreds of participants in a crowd-sourcing framework to obtain scores for a set of semantic descriptors for each clip. Next, we analyze correlations between descriptors and build a semantic control space based on cinematography guidelines and human perception studies. Finally, we learn a generative model that can map a set of desired semantic video descriptors into low-level camera trajectory parameters. We evaluate our system by demonstrating that our model successfully generates shots that are rated by participants as having the expected degrees of expression for each descriptor. We also show that our models generalize to different scenes in both simulation and real-world experiments. Data and video found at: https://sites.google.com/view/robotcam.

Aerial cinematography is significantly expanding the capabilities of film-makers. Recent progress in autonomous unmanned aerial vehicles (UAVs) has further increased the potential impact of aerial cameras, with systems that can safely track actors in unstructured cluttered environments. Professional productions, however, require the use of multiple cameras simultaneously to record different viewpoints of the same scene, which are edited into the final footage either in real time or in post-production. Such extreme motion coordination is particularly hard for unscripted action scenes, which are a common use case of aerial cameras. In this work we develop a real-time multi-UAV coordination system that is capable of recording dynamic targets while maximizing shot diversity and avoiding collisions and mutual visibility between cameras. We validate our approach in multiple cluttered environments of a photo-realistic simulator, and deploy the system using two UAVs in real-world experiments. We show that our coordination scheme has low computational cost and takes only 1.17 ms on average to plan for a team of 3 UAVs over a 10 s time horizon. Supplementary video: https://youtu.be/m2R3anv2ADE

Aerial vehicles are revolutionizing applications that require capturing the 3D structure of dynamic targets in the wild, such as sports, medicine and entertainment. The core challenges in developing a motion-capture system that operates in outdoors environments are: (1) 3D inference requires multiple simultaneous viewpoints of the target, (2) occlusion caused by obstacles is frequent when tracking moving targets, and (3) the camera and vehicle state estimation is noisy. We present a real-time aerial system for multi-camera control that can reconstruct human motions in natural environments without the use of special-purpose markers. We develop a multi-robot coordination scheme that maintains the optimal flight formation for target reconstruction quality amongst obstacles. We provide studies evaluating system performance in simulation, and validate real-world performance using two drones while a target performs activities such as jogging and playing soccer. Supplementary video: https://youtu.be/jxt91vx0cns

Machines are a long way from robustly solving open-world perception-control tasks, such as first-person view (FPV) aerial navigation. While recent advances in end-to- end Machine Learning, especially Imitation Learning and Reinforcement appear promising, they are constrained by the need of large amounts of difficult-to-collect labeled real- world data. Simulated data, on the other hand, is easy to generate, but generally does not render safe behaviors in diverse real-life scenarios. In this work we propose a novel method for learning robust visuomotor policies for real-world deployment which can be trained purely with simulated data. We develop rich state representations that combine supervised and unsupervised environment data. Our approach takes a cross-modal perspective, where separate modalities correspond to the raw camera data and the system states relevant to the task, such as the relative pose of gates to the drone in the case of drone racing. We feed both data modalities into a novel factored architecture, which learns a joint lowdimensional embedding via Variational Auto Encoders. This compact representation is then fed into a control policy, which we trained using imitation learning with expert trajectories in a simulator. We analyze the rich latent spaces learned with our proposed representations, and show that the use of our cross-modal architecture significantly improves control policy performance as compared to end-to-end learning or purely unsupervised feature extractors. We also present real-world results for drone navigation through gates in different track configurations and environmental conditions. Our proposed method, which runs fully onboard, can successfully generalize the learned representations and policies across simulation and reality, significantly outperforming baseline approaches.

In the task of Autonomous aerial filming of a moving actor (e.g. a person or a vehicle), it is crucial to have a good heading direction estimation for the actor from the visual input. However, the models obtained in other similar tasks, such as pedestrian collision risk analysis and human-robot interaction, are very difficult to generalize to the aerial filming task, because of the difference in data distributions. Towards improving generalization with less amount of labeled data, this paper presents a semi-supervised algorithm for heading direction estimation problem. We utilize temporal continuity as the unsupervised signal to regularize the model and achieve better generalization ability. This semi-supervised algorithm is applied to both training and testing phases, which increases the testing performance by a large margin. We show that by leveraging unlabeled sequences, the amount of labeled data required can be significantly reduced. We also discuss several important details on improving the performance by balancing labeled and unlabeled loss, and making good combinations. Experimental results show that our approach robustly outputs the heading direction for different types of actor. The aesthetic value of the video is also improved in the aerial filming task.

The use of drones for aerial cinematography has revolutionized several applications and industries that require live and dynamic camera viewpoints such as entertainment, sports, and security. However, safely controlling a drone while filming a moving target usually requires multiple expert human operators; hence the need for an autonomous cinematographer. Current approaches have severe real-life limitations such as requiring fully scripted scenes, high-precision motion-capture systems or GPS tags to localize targets, and prior maps of the environment to avoid obstacles and plan for occlusion.In this work, we overcome such limitations and propose a complete system for aerial cinematography that combines: (1) a vision-based algorithm for target localization; (2) a real-time incremental 3D signed-distance map algorithm for occlusion and safety computation; and (3) a real-time camera motion planner that optimizes smoothness, collisions, occlusions and artistic guidelines. We evaluate robustness and real-time performance in series of field experiments and simulations by tracking dynamic targets moving through unknown, unstructured environments. Finally, we verify that despite removing previous limitations, our system achieves state-of-the-art performance.

Aerial filming is constantly gaining importance due to the recent advances in drone technology. It invites many intriguing, unsolved problems at the intersection of aesthetical and scientific challenges. In this work, we propose a deep reinforcement learning agent which supervises motion planning of a filming drone by making desirable shot mode selections based on aesthetical values of video shots. Unlike most of the current state-of-the-art approaches that require explicit guidance by a human expert, our drone learns how to make favorable viewpoint selections by experience. We propose a learning scheme that exploits aesthetical features of retrospective shots in order to extract a desirable policy for better prospective shots. We train our agent in realistic AirSim simulations using both a hand-crafted reward function as well as reward from direct human input. We then deploy the same agent on a real DJI M210 drone in order to test the generalization capability of our approach to real world conditions. To evaluate the success of our approach in the end, we conduct a comprehensive user study in which participants rate the shot quality of our methods. Videos of the system in action can be seen at https://youtu.be/qmVw6mfyEmw.