arXiv subjects

Merve Atasever

Publications and source records attributed to Merve Atasever.

6 recordsLinked to original sources

arXiv2026

From LLM-Generated Specifications to Learned Quadruped Locomotion

Quadruped robot locomotion policies are often trained using reinforcement learning, which in turn relies heavily on hand-crafted reward functions. Designing reward functions requires substantial manual engineering, and it is often unclear which local rewards will induce the desired global behavior. Shaped rewards from formal specifications in languages like Signal Temporal Logic (STL) can make rewards more interpretable, but writing STL specifications itself still requires domain expertise. We study whether large language models (LLMs) can fill this gap by generating Parametric Signal Temporal Logic (PSTL) specifications that are subsequently used for policy learning. Given a natural language locomotion objective and a constrained specification grammar, GPT-5.5 and Qwen 3.6 independently propose STL templates for command tracking, safety, and gait structure. We instantiate the parameters of the generated PSTL templates using expert trajectories and retain only specifications that are consistent with demonstrated expert behavior. The resulting specifications are then transformed into smooth, finite-history reward functions and used to train a quadruped locomotion policy with Proximal Policy Optimization (PPO) in MuJoCo XLA (MJX). We evaluate both \emph{gait-aware} and \emph{gait-agnostic} settings. The former specifies walking-trot, trot, and bound regimes, while the latter allows contact patterns to emerge from the task objective. We compare against hand-engineered rewards, Text2Reward-style LLM-generated reward code, and an expert-switching oracle. Gait-aware Qwen 3.6 specifications achieved 100\% survival and command success across all tested speeds (0.3--2.1 m/s) and matched the target gait at high speeds, whereas Text2Reward achieved 0\% for both metrics at $\geq 1.9$ m/s. Videos: https://stl-locomotion.github.io/

cs.RO↗

arXiv2026

Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications

Reinforcement learning (RL) for quadruped locomotion commonly depends on fixed, hand-crafted, and Markovian reward functions that limit both interpretability of learned policies and lack explicit control over gait behaviors. We introduce a framework where distinct gaits are specified using parameterized constraints expressed in Signal Temporal Logic (STL). These include safety bounds, gait synchronization constraints, command tracking, and actuation bounds. From these specifications, we develop a reward shaping mechanism that provides learning agents a dense, continuous reward landscape that encodes desired behavior. We define parametric STL templates for three speed regimes (walking-trot, trot, bound), calibrate their parameters from reference rollouts, and compute rewards from using smooth approximations of STL robustness over the rollouts. The generated rewards can be used to provide shaped gradients compatible with Proximal Policy Optimization (PPO). We instantiate the approach on Google's Barkour quadruped robot in MuJoCo XLA (MJX). We use parallelization within the simulator to improve training speeds and use domain randomization to robustify learned policies. We show that compared to a baseline of hand-crafted rewards, the STL-shaped rewards yield tighter velocity tracking and more stable training. Videos can be found on our project website: https://stl-locomotion.github.io/.

cs.RO↗

arXiv2025

Multi-Agent Path Finding via Offline RL and LLM Collaboration

Multi-Agent Path Finding (MAPF) poses a significant and challenging problem critical for applications in robotics and logistics, particularly due to its combinatorial complexity and the partial observability inherent in realistic environments. Decentralized reinforcement learning methods commonly encounter two substantial difficulties: first, they often yield self-centered behaviors among agents, resulting in frequent collisions, and second, their reliance on complex communication modules leads to prolonged training times, sometimes spanning weeks. To address these challenges, we propose an efficient decentralized planning framework based on the Decision Transformer (DT), uniquely leveraging offline reinforcement learning to substantially reduce training durations from weeks to mere hours. Crucially, our approach effectively handles long-horizon credit assignment and significantly improves performance in scenarios with sparse and delayed rewards. Furthermore, to overcome adaptability limitations inherent in standard RL methods under dynamic environmental changes, we integrate a large language model (GPT-4o) to dynamically guide agent policies. Extensive experiments in both static and dynamically changing environments demonstrate that our DT-based approach, augmented briefly by GPT-4o, significantly enhances adaptability and performance.

cs.MA↗

arXiv2025

Self-driving cars: Are we there yet?

Autonomous driving remains a highly active research domain that seeks to enable vehicles to perceive dynamic environments, predict the future trajectories of traffic agents such as vehicles, pedestrians, and cyclists and plan safe and efficient future motions. To advance the field, several competitive platforms and benchmarks have been established to provide standardized datasets and evaluation protocols. Among these, leaderboards by the CARLA organization and nuPlan and the Waymo Open Dataset have become leading benchmarks for assessing motion planning algorithms. Each offers a unique dataset and challenging planning problems spanning a wide range of driving scenarios and conditions. In this study, we present a comprehensive comparative analysis of the motion planning methods featured on these three leaderboards. To ensure a fair and unified evaluation, we adopt CARLA leaderboard v2.0 as our common evaluation platform and modify the selected models for compatibility. By highlighting the strengths and weaknesses of current approaches, we identify prevailing trends, common challenges, and suggest potential directions for advancing motion planning research.

cs.RO↗

arXiv2025

Coordinating Spinal and Limb Dynamics for Enhanced Sprawling Robot Mobility

Sprawling locomotion in vertebrates, particularly salamanders, demonstrates how body undulation and spinal mobility enhance stability, maneuverability, and adaptability across complex terrains. While prior work has separately explored biologically inspired gait design or deep reinforcement learning (DRL), these approaches face inherent limitations: open-loop gait designs often lack adaptability to unforeseen terrain variations, whereas end-to-end DRL methods are data-hungry and prone to unstable behaviors when transferring from simulation to real robots. We propose a hybrid control framework that integrates Hildebrand's biologically grounded gait design with DRL, enabling a salamander-inspired quadruped robot to exploit active spinal joints for robust crawling motion. Our evaluation across multiple robot configurations in target-directed navigation tasks reveals that this hybrid approach systematically improves robustness under environmental uncertainties such as surface irregularities. By bridging structured gait design with learning-based methodology, our work highlights the promise of interdisciplinary control strategies for developing efficient, resilient, and biologically informed spinal actuation in robotic systems.

cs.RO↗

arXiv2024

Motion Planning for Automata-based Objectives using Efficient Gradient-based Methods

In recent years, there has been increasing interest in using formal methods-based techniques to safely achieve temporal tasks, such as timed sequence of goals, or patrolling objectives. Such tasks are often expressed in real-time logics such as Signal Temporal Logic (STL), whereby, the logical specification is encoded into an optimization problem. Such approaches usually involve optimizing over the quantitative semantics, or robustness degree, of the logic over bounded horizons: the semantics can be encoded as mixed-integer linear constraints or into smooth approximations of the robustness degree. A major limitation of this approach is that it faces scalability challenges with respect to temporal complexity: for example, encoding long-term tasks requires storing the entire history of the system. In this paper, we present a quantitative generalization of such tasks in the form of symbolic automata objectives. Specifically, we show that symbolic automata can be expressed as matrix operators that lend themselves to automatic differentiation, allowing for the use of off-the-shelf gradient-based optimizers. We show how this helps solve the need to store arbitrarily long system trajectories, while efficiently leveraging the task structure encoded in the automaton.

cs.FL↗