A quadruped robot is a promising system that can offer assistance comparable to that of guide dogs due to its similar form factor. However, various challenges remain in making these robots a reliable option for blind and low-vision (BLV) individuals. Among these challenges, noise and jerky motion during walking are critical drawbacks of existing quadruped robots. While these issues have largely been overlooked in guide dog robot research, our interviews with guide dog handlers and trainers revealed that acoustic and physical disturbances can be particularly disruptive for BLV individuals, who rely heavily on environmental sounds for navigation. To address these issues, we developed a novel walking controller for slow stepping and smooth foot swing/contact while maintaining human walking speed, as well as robust and stable balance control. The controller integrates with a perception system to facilitate locomotion over non-flat terrains, such as stairs. Our controller was extensively tested on the Unitree Go1 robot and, when compared with other control methods, demonstrated significant noise reduction -- half of the default locomotion controller. To evaluate the usability, workload, and perceived noise of the developed system from a user’s perspective, we conducted indoor walking experiments. In these tests, participants compared our controller with the robot’s default controller. The results demonstrated higher user acceptance of our controller, highlighting its potential to improve the overall user experience of robotic guide dogs.

While commendable progress has been made in user-centric research on mobile assistive systems for blind and low-vision (BLV) individuals, references that directly inform robot navigation design remain rare. To bridge this gap, we conducted a comprehensive human study involving interviews with 26 guide dog handlers, four white cane users, nine guide dog trainers, and one O&M trainer, along with 15+ hours of observing guide dog-assisted walking. After de-identification, we open-sourced the dataset to promote human-centered development and informed decision-making for assistive systems for BLV people. Building on insights from this formative study, we developed GuideNav, a vision-only, teach-and-repeat navigation system. Inspired by how guide dogs are trained and assist their handlers, GuideNav autonomously repeats a path demonstrated by a sighted person using a robot. Specifically, the system constructs a topological representation of the taught route, integrates visual place recognition with temporal filtering, and employs a relative pose estimator to compute navigation actions-all without relying on costly, heavy, power-hungry sensors such as LiDAR. In field tests, GuideNav consistently achieved kilometer-scale route following across five outdoor environments, maintaining reliability despite noticeable scene variations between teach and repeat runs. A user study with 3 guide dog handlers and 1 guide dog trainer further confirmed the system's feasibility, marking, to our knowledge, the first demonstration of a quadruped mobile system guiding a route in a manner comparable to guide dogs.

The ability to push large objects in a goal-directed manner using onboard egocentric perception is an essential skill for humanoid robots to perform complex tasks such as material handling in warehouses. To robustly manipulate heavy objects to arbitrary goal configurations, the robot must cope with unknown object mass and ground friction, noisy onboard perception, and actuation errors; all in a real-time feedback loop. Existing solutions either rely on privileged object-state information without onboard perception or lack robustness to variations in goal configurations and object physical properties. In this work, we present VOFA, a visual goal-conditioned humanoid loco-manipulation system capable of pushing objects with unknown physical properties to arbitrary goal positions. VOFA consists of a two-level hierarchical architecture with a high-level visuomotor policy and a low-level force-adaptive whole-body controller. The high-level policy processes noisy onboard observations and generates goal-conditioned commands to operate in closed loop across diverse object-goal configurations, while the low-level whole-body controller provides robustness to variations in object physical properties. VOFA is extensively evaluated in both simulation and real-world experiments on the Booster T1 humanoid robot. Our results demonstrate strong performance, achieving over 90

Tactile Walking Surface Indicators (TWSIs) are safety-critical landmarks that blind and low-vision (BLV) pedestrians use to locate crossings and hazard zones. From our observation sessions with BLV guide dog handlers, trainers, and an O&M specialist, we confirmed the critical importance of reliable and accurate TWSI segmentation for navigation assistance of BLV individuals. Achieving such reliability requires large-scale annotated data. However, TWSIs are severely underrepresented in existing urban perception datasets, and even existing dedicated paving datasets are limited: they lack robot-relevant viewpoints (e.g., egocentric or top-down) and are geographically biased toward East Asian directional bars - raised parallel strips used for continuous guidance along sidewalks. This narrow focus overlooks truncated domes - rows of round bumps used primarily in North America and Europe as detectable warnings at curbs, crossings, and platform edges. As a result, models trained only on bar-centric data struggle to generalize to dome based warnings, leading to missed detections and false stops in safety critical environments. We introduce GuideTWSI, the largest and most diverse TWSI dataset, which combines a photorealistic synthetic dataset, carefully curated open-source tactile data, and quadruped real-world data collected and annotated by the authors. Notably, we developed an Unreal Engine–based synthetic data generation pipeline to obtain segmented, labeled data across diverse materials, lighting conditions, weather, and robot-relevant viewpoints. Extensive evaluations show that synthetic augmentation improves truncated dome segmentation across diverse state-of-the-art models, with gains of up to +29 mIoU points, and enhances cross-domain robustness. Moreover, real-robot experiments demonstrate accurate stoppings at truncated domes, with high repeatability and stop success rates (96.15%). The GuideTWSI dataset, model weights, and code will be publicly released.

Open-world mapless navigation from sparse language instructions requires resolving underspecified goals and inferring which environmental cues are relevant for reaching the goal. For instance, reaching an out-of-view destination may require interpreting ramps, signs, or detours that reveal where to go or which route to take. Prior works are limited by their reliance on known navigation factors and closed-set factor categories, or identify cues before motion planning and miss plan-dependent cues. We argue that pretrained Vision-Language Models (VLMs) can discover novel instruction-relevant cues, but require adaptation to focus on which cues matter and how they should influence motion planning. We realize these ideas in Foresight, a test-time framework in which a finetuned VLM alternates between proposing image-space motion plans and critiquing them using the language goal and visual context. Subsequent plans are conditioned on prior critiques, enabling iterative motion refinement before execution. To align plan critiques and refinements with open-set behavior preferences, we learn a reward model from human feedback and use it to post-train the VLM with reinforcement learning in the plan-critique loop. In offline evaluations and 6 real-world environments, Foresight improves average task success by 37

In Fall 2023, we introduced a new AI Literacy class called The Essentials of AI for Life and Society (CS 109), a one-credit, seminar course consisting mainly of guest lectures, which was open to the entire university, including students, staff, and faculty. Building on its success and popularity, this paper describes our significant expansion of the course into a full-scale three-credit undergraduate course (CS 309), with an expanded emphasis on student engagement, interactivity, and ethics-related components. To knit together content from the guest lecturers, we implemented a flipped classroom. This model used weekly asynchronous learning modules---integrating pre-recorded expert lectures, collaborative readings, and ethical reflections---which were then unified by the course instructor during a live, interactive discussion session. To maintain the broad accessibility of the material (no prerequisites), the course introduced substantive, non-programming homework assignments in which students applied AI concepts to grounded, real-world problems. This work culminated in a final project analyzing the ethical and societal implications of a chosen AI tool. The redesigned course received overwhelmingly positive student feedback, highlighting its interactivity, coherence, and accessible and engaging assignments. This paper details the course's evolution, its pedagogical structure, and the lessons learned in developing a core AI literacy course. All course materials are freely available for others to use and build upon.

We introduce QUINTIC, a general algorithm for actively learning quantitative automata from preferences. Quantitative automata evaluate input sequences by applying a valuation function---such as sum, product, or average---to the output labels of the states visited. Such models naturally arise in use cases ranging from probabilistic verification, sequence classification, and sequential decision making. However, existing learning approaches, such as variants of L*, weighted‐automata learning algorithms, and active learning preference‐driven methods, either assume finite output alphabets or restrict the valuation function to particular forms. QUINTIC utilizes a symbolic observation table and applies deductive reasoning with the assistance of an SMT solver to identify the correct minimal state, transition, and state label combination of the quantitative automaton. The deductive reasoning relies on the minimal combination of theories determined by the valuation function and output alphabet. Consequently, QUINTIC has completeness, minimalism, and query complexity guarantees, and learns quantitative automata across finite, integer, and rational outputs. Our extensive experiments show how QUINTIC scales under weak or strong feedback, and alternative MaxSMT objectives.

Robots deployed over long periods must reason about environments that change over time. Existing long-term perception systems often address object change reactively, updating their maps only after revisiting a scene and observing that an object has moved. Instead, robots should reason proactively about how long objects are likely to persist using the context in which they appear. For example, a car at a traffic light and a car in a parking spot share the same semantic class, but their contexts imply different persistence durations. We propose PreSIST (Predictive Scene-conditioned Instance Survival over Time), a method for predicting whether an observed object will remain in its last seen pose at arbitrary future times. PreSIST estimates instance-level persistence priors from object properties and scene context, then integrates these priors with a probabilistic persistence filter as observations become available. Its key insight is that the reasoning capabilities of vision-language models (VLMs) can relate scene context to likely object use and human activity, enabling persistence prediction before long-term observations are available. We develop two interchangeable variants: PreSIST-Lang, which estimates persistence priors using a VLM, and PreSIST-Vis, a novel vision-only model trained using PreSIST-Lang pseudo-labels for efficient deployment. Experiments on a new dataset of in-the-wild object persistence annotations show that PreSIST-Lang and PreSIST-Vis outperform baselines on open-world persistence prediction.

Learning fast and robust ball-kicking skills is a critical capability for humanoid soccer robots, yet it remains a challenging problem due to the need for rapid leg swings, postural stability on a single support foot, and robustness under noisy sensory input and external perturbations (e.g., opponents). This paper presents a reinforcement learning (RL)–based training pipeline that enables humanoid robots to execute robust continual ball-kicking with adaptability to different ball-goal configurations. The pipeline extends a typical teacher-student training framework--in which a teacher policy is trained with ground truth state information and the student learns to mimic it with noisy, imperfect sensing--by including four training stages: (1) long-distance ball chasing (teacher); (2) directional kicking (teacher); (3) teacher policy distillation (student), and (4) student adaptation and refinement (student). Key design elements--including tailored reward functions, realistic noise modeling, and online constrained RL for adaptation and refinement--are critical for closing the sim-to-real gap and sustaining performance under perceptual uncertainty. Extensive evaluations in both simulation and on a real robot demonstrate strong kicking accuracy and goal-scoring success across diverse ball–goal configurations. Ablation studies further highlight the necessity of the constrained RL, noise modeling, and the adaptation stage. This work presents a training pipeline for robust continual humanoid ball-kicking under imperfect perception, establishing a benchmark task for visuomotor skill learning in humanoid whole-body control.

Scientific peer review faces mounting strain as submission volumes surge, making it increasingly difficult to sustain review quality, consistency, and timeliness. Recent advances in AI have led the community to consider its use in peer review, yet a key unresolved question is whether AI can generate technically sound reviews at real-world conference scale. Here we report the first large-scale field deployment of AI-assisted peer review: every main-track submission at AAAI-26 received one clearly identified AI review from a state-of-the-art system. The system combined frontier models, tool use, and safeguards in a multi-stage process to generate reviews for all 22,977 full-review papers in less than a day. A large-scale survey of AAAI-26 authors and program committee members showed that participants not only found AI reviews useful, but actually preferred them to human reviews on key dimensions such as technical accuracy and research suggestions. We also introduce a novel benchmark and find that our system substantially outperforms a simple LLM-generated review baseline at detecting a variety of scientific weaknesses. Together, these results show that state-of-the-art AI methods can already make meaningful contributions to scientific peer review at conference scale, opening a path toward the next generation of synergistic human-AI teaming for evaluating research.

Localizing ground robots against aerial imagery provides a critical capability for autonomous navigation, especially in environments where GPS is unreliable or unavailable. This task is challenging due to large viewpoint differences and substantial environmental variability. Most prior methods localize each frame independently, using either global-descriptor retrieval or spatial feature alignment, which leaves them vulnerable to ambiguity and multi-modal pose hypotheses. While sequential reasoning can mitigate this uncertainty, adapting existing per-frame pipelines for sequential use introduces unfavorable trade-offs among accuracy, memory, and computation that limit their practical deployment. We propose BEV-Patch-PF, a vision-only, GPS-free sequential geo-localization system that integrates particle filtering with learned bird’s-eye-view (BEV) and aerial feature maps. For each 3-DoF particle pose hypothesis, we crop the corresponding patch from an aerial feature map computed from a local aerial image centered on the predicted pose. The resulting BEV–aerial feature match defines a per-particle log-likelihood for particle-filter updates. In addition, we learn a frame-level uncertainty estimate that adaptively flattens the observation likelihood for unreliable observations, preventing overconfident particle collapse in ambiguous regions. On two real-world off-road datasets, our method achieves 9.7 lower absolute trajectory error (ATE) on seen routes and 6.6 lower ATE on unseen routes than a retrieval-based baseline, while remaining robust under partial canopy cover and shadowing. The system runs in real time at 10 Hz on an NVIDIA Tesla T4, enabling practical robot deployment.

Mobile service robots can benefit from object-level understanding of their environments, including the ability to distinguish object instances and re-identify previously seen instances. Object re-identification is challenging across different viewpoints and in scenes with significant appearance variation arising from weather or lighting changes. Existing works on object re-identification either focus on specific classes or require foreground segmentation. Further, these methods, along with object re-identification datasets, have limited consideration of challenges such as outdoor scenes and illumination changes. To address this problem, we introduce CODa Re-ID: an in-the-wild object re-identification dataset containing 1,037,814 observations of 557 objects across 8 classes under diverse lighting conditions and viewpoints. Further, we propose CLOVER, a representation learning method for object observations that can distinguish between static object instances without requiring foreground segmentation. We also introduce MapCLOVER, a method for scalably summarizing CLOVER descriptors for use in object maps and matching new observations to summarized descriptors. Our results show that CLOVER achieves superior performance in static object re-identification under varying lighting conditions and viewpoint changes and can generalize to unseen instances and classes.

Large language models (LLMs) already excel at writing code in high-resource languages such as Python and JavaScript, yet stumble on low-resource languages that remain essential to science and engineering. Besides the obvious shortage of pre-training data, post-training itself is a bottleneck: every new language seems to require new datasets, test harnesses, and reinforcement learning (RL) infrastructure. We introduce Agnostics, a language-agnostic post-training pipeline that eliminates this per-language engineering. The key idea is to judge code solely by its externally observable behavior, so a single verifier can test solutions written in any language. Concretely, we (i) use an LLM to rewrite existing unit-test datasets into an I/O format, (ii) supply a short configuration that tells the verifier how to compile and run a target language, and (iii) apply reinforcement learning with verifiable rewards (RLVR) in a robust code execution environment. Applied to five low-resource languages—Lua, Julia, R, OCaml, and Fortran—Agnostics (1) improves Qwen-3 4B to performance that rivals other 16B–70B open-weight models; (2) scales cleanly to larger and diverse model families (Qwen-3 8B, DeepSeek Coder 6.7B Instruct, SmolLM3, Phi 4 Mini); and (3) for open-weight models with ≤16B parameters, sets new state-of-the-art pass@1 results on MultiPL-E and a new multi-language version of LiveCodeBench that we introduce. We will release the language-agnostic training datasets (Ag-MBPP-X, Ag-Codeforces-X, Ag-LiveCodeBench-X), training code, and ready-to-use configurations, making RL post-training in any programming language as simple as editing a short YAML file.

Robots must adapt to diverse human instructions and operate safely in unstructured, open-world environments. Recent Vision–Language models (VLMs) offer strong priors for grounding language and perception, but remain difficult to steer for navigation due to differences in action spaces and pretraining objectives that hamper transferability to robotics tasks. Towards addressing this, we introduce Ventura, a vision–language navigation system that finetunes internet-pretrained image diffusion models for path planning. Instead of directly predicting low-level actions, Ventura generates a path mask (i.e. a visual plan) in image space that captures fine-grained, context-aware navigation behaviors. A lightweight behavior-cloning policy grounds these visual plans into executable trajectories, yielding an interface that follows natural language instructions to generate diverse robot behaviors. To scale training, we supervise on path masks derived from self-supervised tracking models paired with VLM-augmented captions, avoiding manual pixel-level annotation or highly engineered data collection setups. In extensive real-world evaluations, Ventura outperforms state-of-the-art foundation model baselines on object reaching, obstacle avoidance, and terrain preference tasks, improving success rates by 33% and reducing collisions by 54% across both seen and unseen scenarios. Notably, we find that Ventura generalizes to unseen combinations of distinct tasks, revealing emergent compositional capabilities. Videos, code, and additional materials: https://venturapath.github.io.

Aerial imagery provides essential global context for autonomous navigation, enabling route planning at scales inaccessible to onboard sensing. We address the problem of generating global costmaps for long-range planning directly from satellite imagery when entities and mission-specific traversal rules are expressed in natural language at test time. This setting is challenging since mission requirements vary, terrain entities may be unknown at deployment, and user prompts often encode compositional traversal logic. Existing approaches relying on fixed ontologies and static cost mappings cannot accommodate such flexibility. While foundation models excel at language interpretation and open-vocabulary perception, no single model can simultaneously parse nuanced mission directives, locate arbitrary entities in large-scale imagery, and synthesize them into an executable cost function for planners. We therefore propose OVerSeeC, a zero-shot modular framework that decomposes the problem into Interpret–Locate–Synthesize: (i) an LLM extracts entities and ranked preferences, (ii) an open-vocabulary segmentation pipeline identifies these entities from high-resolution imagery, and (iii) the LLM uses user's natural language preferences and masks to synthesize executable costmap code. Empirically, OVerSeeC handles novel entities, respects ranked and compositional preferences, and produces routes consistent with human-drawn trajectories across diverse regions, demonstrating robustness to distribution shifts. This shows that modular composition of foundation models enables open-vocabulary, preference-aligned costmap generation for scalable, mission-adaptive global planning.

In autonomous robot navigation, terrain cost assignment is typically performed using a semantics-based paradigm in which terrain is first labeled using a pre-trained semantic classifier and costs are then assigned according to a user-defined mapping between label and cost. While this approach is rapidly adaptable to changing user preferences, only preferences over the types of terrain that are already known by the semantic classifier can be expressed. In this paper, we hypothesize that a machine-learning-based alternative to the semantics-based paradigm above will allow for rapid cost assignment adaptation to preferences expressed over new terrains at deployment time without the need for additional training. To investigate this hypothesis, we introduce and study PACER, a novel approach to costmap generation that accepts as input a single birds-eye view (BEV) image of the surrounding area along with a user-specified preference context and generates a corresponding BEV costmap that aligns with the preference context. Using both real and synthetic data along with a combination of proposed training tasks, we find that PACER is able to adapt quickly to new user preferences while also exhibiting better generalization to novel terrains compared to both semantics-based and representation-learning approaches.

ABSTRACT This study examines how socially compliant robot behaviours, operationalized as body language and verbal cues, affect human perceptions of social intelligence and compliance with a quadruped robot during incidental human–robot encounters. Extending prior work that primarily focused on direct human–robot interactions, this study addresses the understudied context of incidental encounters, which are brief, unplanned interactions between bystanders and autonomous robots in public environments. In an online video‐based study with 385 participants using a within‐subject design, we found that both verbal and body language behaviours significantly improved the robot's perceived social intelligence (PSI), which in turn positively correlated with human compliance. Verbal communication alone increased compliance likelihood more than body language, and combining both yielded the highest PSI ratings and compliance scores. To validate these findings beyond controlled video scenarios, a follow‐up real‐world study with 26 participants replicated the results: 11 out of 13 of participants complied in the Body Language + Verbal condition versus only 1 in the baseline condition. Free‐text responses revealed the importance of clearly stated intentions, politeness, and concerns about robot legitimacy and safety. Together, these findings highlight the critical role of perceived social intelligence in fostering human assistance for robots during incidental encounters and offer design strategies to support robot deployment in public environments.

Service robots must retrieve objects in dynamic, open-world settings where requests may reference attributes (“the red mug”), spatial context (“the mug on the table”), or past states (“the mug that was here yesterday”). Existing approaches capture only parts of this problem: scene graphs capture spatial relations but ignore temporal grounding, temporal reasoning methods model dynamics but do not support embodied interaction, and dynamic scene graphs handle both but remain closed-world with fixed vocabularies. We present STAR (SpatioTemporal Active Retrieval), a framework that unifies memory queries and embodied actions within a single decision loop. STAR leverages a non-parametric long-term memory and a working memory to support efficient recall, and uses a vision-language model to select either temporal or spatial actions at each step. We introduce STARBench, a benchmark of spatiotemporal object search tasks across simulated and real environments. Experiments on STARBench and on a Tiago robot show that STAR consistently outperforms scene-graph and memory-only baselines, demonstrating the benefits of treating search in time and search in space as a unified problem.

High-speed off-road autonomy requires precise closed-loop control for a target vehicle while remaining robust across changing terrains. Recent forward kinodynamic (FKD) prediction foundation models suggest a promising path, starting from a generalist model and specializing it to the target platform. However, effective specialization remains challenging, as it often requires substantial real-world data, and models adapted to one setting can still overfit to specific terrains or driving regimes. We present OptCar (Optimized Car), a recipe for bridging the gap from generalist to specialist FKD models that preserves cross-terrain generalization while optimizing performance for a specific vehicle. introduces a history-conditioned dynamics adaptation module that encodes recent state-action observations into a dynamics context token, and then fine-tunes the generalist model using limited real-world data together with targeted synthetic rollouts from environment-specific system identification. In closed-loop model predictive control (MPC) experiments across three terrains and an out-of-distribution cart-pulling task, the largest gains appear at 6 m/s, the highest speed evaluated and the regime in which slip dominates tracking error. On vegetation and dirt, the most slip-diverse terrain, OptCar reduces 6 m/s trajectory tracking error by roughly 55

We study the problem of robot navigation in dense and interactive crowds with static constraints such as corridors and furniture. Previous methods fail to consider all types of spatial and temporal interactions among agents and obstacles, leading to unsafe and inefficient robot paths. In this article, we leverage a graph-based representation of crowded and constrained scenarios and propose a structured framework to learn robot navigation policies with deep reinforcement learning. We first split the representations of different inputs, and propose a heterogeneous spatio-temporal (st) graph to model distinct interactions among humans, robots, and obstacles. Based on the heterogeneous st-graph, we propose HEIGHT, a novel navigation policy network architecture with different components to capture heterogeneous interactions through space and time. HEIGHT utilizes attention mechanisms to prioritize important interactions and a recurrent network to track changes in the dynamic scene over time, encouraging the robot to avoid collisions adaptively. Through extensive simulation and real-world experiments, we demonstrate that HEIGHT outperforms state-of-the-art baselines in terms of success, navigation time, and generalization to domain shifts in challenging navigation scenarios. Note to Practitioners-This work is motivated by the challenge of safe and efficient robot navigation in indoor environments with people, such as homes and offices. Conventional navigation methods make simplistic assumptions about interactions among agents and entities, which leads to unsafe or unnatural robot behavior in dynamic settings. Previous machine learning methods either ignore or use ineffective approaches to handle static obstacles-limiting their real-world applicability. For a practical system to reason about both dynamic people and static constraints simultaneously, the following two factors are critical: how the robot represents its surroundings and how it make decisions. To represent the dynamic environment, our method treats people and obstacles differently and keeps the most essential information as inputs. On the architectural side, we propose a structured graph-based network, which consists of specialized models to explicitly models different types of interactions among all observed entities. In challenging simulation benchmarks, our approach outperforms alternative designs that are commonly used in existing works. We also demonstrate strong real-world deployment in everyday environments. To improve deployment, a future direction is continual learning in the real-world. More information is available at https://sites.google.com/view/crowdnav-height/home.