Christian Ellis

Rohan Siva, Neel P. Bhatt, Yunhao Yang et al.

Existing robot planning systems rely on appearance-based reasoning, where visual observations are encoded into latent spaces organized around object appearances (e.g., recognizing a "cart" based on how it looks). However, planning requires reasoning about task-relevant functionalities of objects (e.g., whether an object is "movable"), which appearance-based latent spaces do not capture. As a result, existing approaches struggle to generalize to novel robot-object interactions. We address this limited generalizability through affordance reasoning, enabling planning based on task-relevant object functionalities instead of appearance alone. We introduce A4D, which maps visual observations into a shared latent space structured around affordances (e.g., "movable"). By projecting visual observations into this functional latent space and measuring their proximity to affordances, A4D infers functionalities relevant to the observed object. Furthermore, we introduce an affordance discovery mechanism that expands the latent space to handle unseen scenarios where existing affordances are insufficient. A4D uses proximity in the functional latent space to quantify uncertainty in affordance inference and selectively triggers affordance discovery. We evaluate A4D across several planning tasks involving diverse and unseen affordances. A4D achieves 94% inference accuracy on existing affordances outperforming state-of-the-art approaches by over 15% points, improves new-affordance inference accuracy from 70% to over 90% with fewer than 10% of the original training data, and enables 100x faster inference. Code, videos, and data available at: https://A4Dance-reasoning.github.io.

William Ward, Sarah Etter, Jesse Quattrociocchi et al.

Autonomous robots must go from zero prior knowledge to safe control within seconds to operate in unstructured environments. Abrupt terrain changes, such as a sudden transition to ice, create dynamics shifts that can destabilize planners unless the model adapts in real-time. We present a method for online adaptation that combines function encoders with recursive least squares, treating the function encoder coefficients as latent states updated from streaming odometry. This yields constant-time coefficient estimation without gradient-based inner-loop updates, enabling adaptation from only a few seconds of data. We evaluate our approach on a Van der Pol system to highlight algorithmic behavior, in a Unity simulator for high-fidelity off-road navigation, and on a Clearpath Jackal robot, including on a challenging terrain at a local ice rink. Across these settings, our method improves model accuracy and downstream planning, reducing collisions compared to static and meta-learning baselines.

Franck Djeumou, Christian Ellis, Murat Cubuktepe et al.

In inverse reinforcement learning (IRL), a learning agent infers a reward function encoding the underlying task using demonstrations from experts. However, many existing IRL techniques make the often unrealistic assumption that the agent has access to full information about the environment. We remove this assumption by developing an algorithm for IRL in partially observable Markov decision processes (POMDPs). We address two limitations of existing IRL techniques. First, they require an excessive amount of data due to the information asymmetry between the expert and the learner. Second, most of these IRL techniques require solving the computationally intractable forward problem -- computing an optimal policy given a reward function -- in POMDPs. The developed algorithm reduces the information asymmetry while increasing the data efficiency by incorporating task specifications expressed in temporal logic into IRL. Such specifications may be interpreted as side information available to the learner a priori in addition to the demonstrations. Further, the algorithm avoids a common source of algorithmic complexity by building on causal entropy as the measure of the likelihood of the demonstrations as opposed to entropy. Nevertheless, the resulting problem is nonconvex due to the so-called forward problem. We solve the intrinsic nonconvexity of the forward problem in a scalable manner through a sequential linear programming scheme that guarantees to converge to a locally optimal policy. In a series of examples, including experiments in a high-fidelity Unity simulator, we demonstrate that even with a limited amount of data and POMDPs with tens of thousands of states, our algorithm learns reward functions and policies that satisfy the task while inducing similar behavior to the expert by leveraging the provided side information.

Tianyu Qiu, Filippos Fotiadis, Xinjie Liu et al.

Linear-quadratic Gaussian games provide a framework for modeling strategic interactions in multi-agent systems, where agents must estimate system states from noisy observations while also making decisions to optimize a quadratic cost. However, these formulations usually require agents to utilize the full set of available observations when forming their state estimates, which can be unrealistic in large-scale or resource-constrained settings. In this paper, we consider linear-quadratic Gaussian games with sparse interagent observations. To enforce sparsity in the estimation stage, we design a distributed estimator that balances estimation effectiveness with interagent measurement sparsity via a group lasso problem, while agents implement feedback Nash strategies based on their state estimates. We provide sufficient conditions under which the sparse estimator is guaranteed to trigger a corrective reset to the optimal estimation gain, ensuring that estimation quality does not degrade beyond a level determined by the regularization parameters. Simulations on a formation game show that the proposed approach yields a significant reduction in communication resources consumed while only minimally affecting the nominal equilibrium trajectories.

Dongmyeong Lee, Jesse Quattrociocchi, Christian Ellis et al.

We propose BEV-Patch-PF, a GPS-free sequential geo-localization system that integrates a particle filter with learned bird's-eye-view (BEV) and aerial feature maps. From onboard RGB and depth images, we construct a BEV feature map. For each 3-DoF particle pose hypothesis, we crop the corresponding patch from an aerial feature map computed from a local aerial image queried around the approximate location. BEV-Patch-PF computes a per-particle log-likelihood by matching the BEV feature to the aerial patch feature. On two real-world off-road datasets, our method achieves 7.5x lower absolute trajectory error (ATE) on seen routes and 7.0x lower ATE on unseen routes than a retrieval-based baseline, while maintaining accuracy under dense canopy and shadow. The system runs in real time at 10 Hz on an NVIDIA Tesla T4, enabling practical robot deployment.

Tianyu Qiu, Eric Ouano, Fernando Palafox et al.

While game-theoretic planning frameworks are effective at modeling multi-agent interactions, they require solving large optimization problems where the number of variables increases with the number of agents, resulting in long computation times that limit their use in large-scale, real-time systems. To address this issue, we propose 1) PSN Game-a learning-based, game-theoretic prediction and planning framework that reduces game size by learning a Player Selection Network (PSN); and 2) a Goal Inference Network (GIN) that makes it possible to use the PSN in incomplete-information games where other agents' intentions are unknown to the ego agent. A PSN outputs a player selection mask that distinguishes influential players from less relevant ones, enabling the ego player to solve a smaller, masked game involving only selected players. By reducing the number of players included in the game, PSN shrinks the corresponding optimization problems, leading to faster solve times. Experiments in both simulated scenarios and real-world pedestrian trajectory datasets show that PSN is competitive with, and often improves upon, the evaluated explicit game-theoretic selection baselines in 1) prediction accuracy and 2) planning safety. Across scenarios, PSN typically selects substantially fewer players than are present in the full game, thereby reducing game size and planning complexity. PSN also generalizes to settings in which agents' objectives are unknown, via the GIN, without test-time fine-tuning. By selecting only the most relevant players for decision-making, PSN Game provides a practical mechanism for reducing planning complexity that can be integrated into existing multi-agent planning frameworks.

Hamzah Khan, Dong Ho Lee, Jingqi Li et al.

Multi-robot coordination often exhibits hierarchical structure, with some robots' decisions depending on the planned behaviors of others. While game theory provides a principled framework for such interactions, existing solvers struggle to handle mixed information structures that combine simultaneous (Nash) and hierarchical (Stackelberg) decision-making. We study N-robot forest-structured mixed-hierarchy games, in which each robot acts as a Stackelberg leader over its subtree while robots in different branches interact via Nash equilibria. We derive the Karush-Kuhn-Tucker (KKT) first-order optimality conditions for this class of games and show that they involve increasingly high-order derivatives of robots' best-response policies as the hierarchy depth grows, rendering a direct solution intractable. To overcome this challenge, we introduce a quasi-policy approximation that removes higher-order policy derivatives and develop an inexact Newton method for efficiently solving the resulting approximated KKT systems. We prove local exponential convergence of the proposed algorithm for games with non-quadratic objectives and nonlinear constraints. The approach is implemented in a highly optimized Julia library (MixedHierarchyGames.jl) and evaluated in hardware and simulated multi-agent experiments, demonstrating real-time convergence for complex mixed-hierarchy information structures.

Xinjie Liu, Cyrus Neary, Kushagra Gupta et al.

Many reinforcement learning (RL) algorithms are impractical for deployment in operational systems or for training with computationally expensive high-fidelity simulations, as they require large amounts of data. Meanwhile, low-fidelity simulators -- such as reduced-order models, heuristic rewards, or generative world models -- can cheaply provide useful data for RL training, even if they are too coarse for zero-shot transfer. We propose multi-fidelity policy gradients (MFPGs), an RL framework that mixes a small amount of data from the target environment with a control variate formed from a large volume of low-fidelity simulation data to construct an unbiased, variance-reduced estimator for on-policy policy gradients. We instantiate the framework with a multi-fidelity variant of the classical REINFORCE algorithm. We show that under standard assumptions, the MFPG estimator guarantees asymptotic convergence of REINFORCE to locally optimal policies in the target environment, and achieves faster finite-sample convergence rates compared to training with high-fidelity data alone. Empirically, we evaluate the MFPG algorithm across a suite of simulated robotics benchmark tasks with limited high-fidelity data but abundant off-dynamics, low-fidelity data. With mild-moderate dynamics gaps, MFPG reliably improves the median performance over a high-fidelity-only baseline, matching the performance of leading multi-fidelity baselines despite its simplicity and minimal tuning overhead. Under large dynamics gaps, MFPG demonstrates the strongest robustness among the evaluated multi-fidelity approaches. An additional experiment shows that MFPG can remain effective even under low-fidelity reward misspecification. Thus, MFPG not only offers a novel paradigm for efficient sim-to-real transfer but also provides a principled approach to managing the trade-off between policy performance and data collection costs.

Christian Ellis, Maggie Wigness, Craig Lennon et al.

Rapid progress in terrain-aware autonomous ground navigation has been driven by advances in supervised semantic segmentation. However, these methods rely on costly data collection and labor-intensive ground truth labeling to train deep models. Furthermore, autonomous systems are increasingly deployed in unrehearsed, unstructured environments where no labeled data exists and semantic categories may be ambiguous or domain-specific. Recent zero-shot approaches to unsupervised segmentation have shown promise in such settings but typically operate on individual frames, lacking temporal consistency-a critical property for robust perception in unstructured environments. To address this gap we introduce Frontier-Seg, a method for temporally consistent unsupervised segmentation of terrain from mobile robot video streams. Frontier-Seg clusters superpixel-level features extracted from foundation model backbones-specifically DINOv2-and enforces temporal consistency across frames to identify persistent terrain boundaries or frontiers without human supervision. We evaluate Frontier-Seg on a diverse set of benchmark datasets-including RUGD and RELLIS-3D-demonstrating its ability to perform unsupervised segmentation across unstructured off-road environments.

Yunhao Yang, Neel P. Bhatt, Christian Ellis et al.

Logistics operators, from battlefield coordinators rerouting airlifts ahead of a storm to warehouse managers juggling late trucks, often face life-critical decisions that demand both domain expertise and rapid and continuous replanning. While popular methods like integer programming yield logistics plans that satisfy user-defined logical constraints, they are slow and assume an idealized mathematical model of the environment that does not account for uncertainty. On the other hand, large language models (LLMs) can handle uncertainty and promise to accelerate replanning while lowering the barrier to entry by translating free-form utterances into executable plans, yet they remain prone to misinterpretations and hallucinations that jeopardize safety and cost. We introduce a neurosymbolic framework that pairs the accessibility of natural-language dialogue with verifiable guarantees on goal interpretation. It converts user requests into structured planning specifications, quantifies its own uncertainty at the field and token level, and invokes an interactive clarification loop whenever confidence falls below an adaptive threshold. A lightweight model, fine-tuned on just 100 uncertainty-filtered examples, surpasses the zero-shot performance of GPT-4.1 while cutting inference latency by nearly 50%. These preliminary results highlight a practical path toward certifiable, real-time, and user-aligned decision-making for complex logistics.

Zhiyun Deng, Dongmyeong Lee, Amanda Adkins et al.

Robust cross-view 3-DoF localization in GPS-denied, off-road environments remains challenging due to (1) perceptual ambiguities from repetitive vegetation and unstructured terrain, and (2) seasonal shifts that significantly alter scene appearance, hindering alignment with outdated satellite imagery. To address this, we introduce MoViX, a self-supervised cross-view video localization framework that learns viewpoint- and season-invariant representations while preserving directional awareness essential for accurate localization. MoViX employs a pose-dependent positive sampling strategy to enhance directional discrimination and temporally aligned hard negative mining to discourage shortcut learning from seasonal cues. A motion-informed frame sampler selects spatially diverse frames, and a lightweight temporal aggregator emphasizes geometrically aligned observations while downweighting ambiguous ones. At inference, MoViX runs within a Monte Carlo Localization framework, using a learned cross-view matching module in place of handcrafted models. Entropy-guided temperature scaling enables robust multi-hypothesis tracking and confident convergence under visual ambiguity. We evaluate MoViX on the TartanDrive 2.0 dataset, training on under 30 minutes of data and testing over 12.29 km. Despite outdated satellite imagery, MoViX localizes within 25 meters of ground truth 93% of the time, and within 50 meters 100% of the time in unseen regions, outperforming state-of-the-art baselines without environment-specific tuning. We further demonstrate generalization on a real-world off-road dataset from a geographically distinct site with a different robot platform.

Christian Ellis, Maggie Wigness, John G. Rogers et al.

Traditional imitation learning provides a set of methods and algorithms to learn a reward function or policy from expert demonstrations. Learning from demonstration has been shown to be advantageous for navigation tasks as it allows for machine learning non-experts to quickly provide information needed to learn complex traversal behaviors. However, a minimal set of demonstrations is unlikely to capture all relevant information needed to achieve the desired behavior in every possible future operational environment. Due to distributional shift among environments, a robot may encounter features that were rarely or never observed during training for which the appropriate reward value is uncertain, leading to undesired outcomes. This paper proposes a Bayesian technique which quantifies uncertainty over the weights of a linear reward function given a dataset of minimal human demonstrations to operate safely in dynamic environments. This uncertainty is quantified and incorporated into a risk averse set of weights used to generate cost maps for planning. Experiments in a 3-D environment with a simulated robot show that our proposed algorithm enables a robot to avoid dangerous terrain completely in two out of three test scenarios and accumulates a lower amount of risk than related approaches in all scenarios without requiring any additional demonstrations.