Ram Vasudevan

This paper develops LongNav-R1, an end-to-end multi-turn reinforcement learning (RL) framework designed to optimize Visual-Language-Action (VLA) models for long-horizon navigation. Unlike existing single-turn paradigm, LongNav-R1 reformulates the navigation decision process as a continuous multi-turn conversation between the VLA policy and the embodied environment. This multi-turn RL framework offers two distinct advantages: i) it enables the agent to reason about the causal effects of historical interactions and sequential future outcomes; and ii) it allows the model to learn directly from online interactions, fostering diverse trajectory generation and avoiding the behavioral rigidity often imposed by human demonstrations. Furthermore, we introduce Horizon-Adaptive Policy Optimization. This mechanism explicitly accounts for varying horizon lengths during advantage estimation, facilitating accurate temporal credit assignment over extended sequences. Consequently, the agent develops diverse navigation behaviors and resists collapse during long-horizon tasks. Experiments on object navigation benchmarks validate the framework's efficacy: With 4,000 rollout trajectories, LongNav-R1 boosts the Qwen3-VL-2B success rate from 64.3% to 73.0%. These results demonstrate superior sample efficiency and significantly outperform state-of-the-art methods. The model's generalizability and robustness are further validated by its zero-shot performance in long-horizon real-world navigation settings. All source code will be open-sourced upon publication.

This letter introduces SLIM-VDB, a new lightweight semantic mapping system with probabilistic semantic fusion for closed-set or open-set dictionaries. Advances in data structures from the computer graphics community, such as OpenVDB, have demonstrated significantly improved computational and memory efficiency in volumetric scene representation. Although OpenVDB has been used for geometric mapping in robotics applications, semantic mapping for scene understanding with OpenVDB remains unexplored. In addition, existing semantic mapping systems lack support for integrating both fixed-category and open-language label predictions within a single framework. In this letter, we propose a novel 3D semantic mapping system that leverages the OpenVDB data structure and integrates a unified Bayesian update framework for both closed- and open-set semantic fusion. Our proposed framework, SLIM-VDB, achieves significant reduction in both memory and integration times compared to current state-of-the-art semantic mapping approaches, while maintaining comparable mapping accuracy.

Neural Radiance Fields and Gaussian Splatting have recently transformed computer vision by enabling photo-realistic representations of complex scenes. However, they have seen limited application in real-world robotics tasks such as trajectory optimization. This is due to the difficulty in reasoning about collisions in radiance models and the computational complexity associated with operating in dense models. This paper addresses these challenges by proposing SPLANNING, a risk-aware trajectory optimizer operating in a Gaussian Splatting model. This paper first derives a method to rigorously upper-bound the probability of collision between a robot and a radiance field. Then, this paper introduces a normalized reformulation of Gaussian Splatting that enables efficient computation of this collision bound. Finally, this paper presents a method to optimize trajectories that avoid collisions in a Gaussian Splat. Experiments show that SPLANNING outperforms state-of-the-art methods in generating collision-free trajectories in cluttered environments. The proposed system is also tested on a real-world robot manipulator. A project page is available at https://roahmlab.github.io/splanning.

Ensuring safe, real-time motion planning in arbitrary environments requires a robotic manipulator to avoid collisions, obey joint limits, and account for uncertainties in the mass and inertia of objects and the robot itself. This paper proposes Autonomous Robust Manipulation via Optimization with Uncertainty-aware Reachability (ARMOUR), a provably-safe, receding-horizon trajectory planner and tracking controller framework for robotic manipulators to address these challenges. ARMOUR first constructs a robust controller that tracks desired trajectories with bounded error despite uncertain dynamics. ARMOUR then uses a novel recursive Newton-Euler method to compute all inputs required to track any trajectory within a continuum of desired trajectories. Finally, ARMOUR over-approximates the swept volume of the manipulator; this enables one to formulate an optimization problem that can be solved in real-time to synthesize provably-safe motions. This paper compares ARMOUR to state of the art methods on a set of challenging manipulation examples in simulation and demonstrates its ability to ensure safety on real hardware in the presence of model uncertainty without sacrificing performance. Project page: https://roahmlab.github.io/armour/.

Designing optimal Bayes filters for nonlinear non-Gaussian systems is a challenging task. The main difficulties are: 1) representing complex beliefs, 2) handling non-Gaussian noise, and 3) marginalizing past states. To address these challenges, we focus on polynomial systems and propose the Max Entropy Moment Kalman Filter (MEM-KF). To address 1), we represent arbitrary beliefs by a Moment-Constrained Max-Entropy Distribution (MED). The MED can asymptotically approximate almost any distribution given an increasing number of moment constraints. To address 2), we model the noise in the process and observation model as MED. To address 3), we propagate the moments through the process model and recover the distribution as MED, thus avoiding symbolic integration, which is generally intractable. All the steps in MEM-KF, including the extraction of a point estimate, can be solved via convex optimization. We showcase the MEM-KF in challenging robotics tasks, such as localization with unknown data association.

Generating optimal trajectories for high-dimensional robotic systems in a time-efficient manner while adhering to constraints is a challenging task. This paper introduces PHLAME, which applies pseudospectral collocation and spatial vector algebra to efficiently solve the Affine Geometric Heat Flow (AGHF) Partial Differential Equation (PDE) for trajectory optimization. Computing a solution to the AGHF PDE scales efficiently because its solution is defined over a two-dimensional domain. To solve the AGHF one usually applies the Method of Lines (MOL), which works by discretizing one variable of the AGHF PDE, effectively converting the PDE into a system of ordinary differential equations (ODEs) that can be solved using standard time-integration methods. Though powerful, this method requires a fine discretization to generate accurate solutions and still requires evaluating the AGHF PDE which can be computationally expensive for high-dimensional systems. PHLAME, overcomes this deficiency by using a pseudospectral method, which reduces the number of function evaluations required to obtain a high-accuracy solution. To further increase computational speed, this paper presents analytical expressions for the AGHF which can be computed efficiently using rigid body dynamics algorithms. The proposed method PHLAME, is tested across various dynamical systems, with and without obstacles and compared to a number of state-of-the-art techniques. PHLAME, is able to generate trajectories for a 44-dimensional state-space system in $\sim 5$ seconds. A project page is available at https://roahmlab.github.io/PHLAME/.

Tails used as inertial appendages induce body rotations of animals and robots—a phenomenon that is governed largely by the ratio of the body and tail moments of inertia. However, vertebrate tails have more degrees of freedom (e.g. number of joints and rotational axes) than most current theoretical models and robotic tails. To understand how morphology affects inertial appendage function, we developed an optimization-based approach that finds the maximally effective tail trajectory and measures error from a target trajectory. For tails of equal total length and mass, increasing the number of equal-length joints increased the complexity of maximally effective tail motions. When we optimized the relative lengths of tail bones while keeping the total tail length, mass and number of joints the same, this optimization-based approach found that the lengths matched the pattern found in the tail bones of mammals specialized for inertial manoeuvring. In both experiments, adding joints enhanced the performance of the inertial appendage, but with diminishing returns, largely due to the total control effort constraint. This optimization-based simulation can compare the maximum performance of diverse inertial appendages that dynamically vary in a moment of inertia in three-dimensional space, predict inertial capabilities from skeletal data and inform the design of robotic inertial appendages.

Numerous complex systems, such as those arisen in ecological networks, genomic contact networks, and social networks, exhibit higher-order and time-varying characteristics, which can be effectively modeled using temporal hypergraphs. However, analyzing and controlling temporal hypergraphs poses significant challenges due to their inherent time-varying and nonlinear nature, while most existing methods predominantly target static hypergraphs. In this article, we generalize the notions of controllability and observability to temporal hypergraphs by leveraging tensor and nonlinear systems theory. Specifically, we establish tensor-based rank conditions to determine the weak controllability and observability of directed, weighted temporal hypergraphs. The proposed framework is further demonstrated with synthetic and real-world examples.

Conventional cameras employed in autonomous vehicle (AV) systems support many perception tasks but are challenged by low-light or high dynamic range scenes, adverse weather, and fast motion. Novel sensors, such as event and thermal cameras, offer capabilities with the potential to address these scenarios, but they remain to be fully exploited. This paper introduces the Novel Sensors for Autonomous Vehicle Perception (NSAVP) dataset to facilitate future research on this topic. The dataset was captured with a platform including stereo event, thermal, monochrome, and RGB cameras as well as a high precision navigation system providing ground truth poses. The data was collected by repeatedly driving two ∼8 km routes and includes varied lighting conditions and opposing viewpoint perspectives. We provide benchmarking experiments on the task of place recognition to demonstrate challenges and opportunities for novel sensors to enhance critical AV perception tasks. To our knowledge, the NSAVP dataset is the first to include stereo thermal cameras together with stereo event and monochrome cameras. The dataset and supporting software suite is available at https://umautobots.github.io/nsavp .