Merve Atasever

Merve Atasever, Cagan Bakirci, Alfredo Reina Corona et al.

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/.

Merve Atasever, Zhuochen Liu, Qingpei Li et al.

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.

Merve Atasever, Ali Okhovat, Azhang Nazaripouya et al.

Among vertebrates, salamanders, with their unique ability to transition between walking and swimming gaits, highlight the role of spinal mobility in locomotion. A flexible spine enables undulation of the body through a wavelike motion along the spine, aiding navigation over uneven terrains and obstacles. Yet environmental uncertainties, such as surface irregularities and variations in friction, can significantly disrupt body-limb coordination and cause discrepancies between predictions from mathematical models and real-world outcomes. Addressing this challenge requires the development of sophisticated control strategies capable of dynamically adapting to uncertain conditions while maintaining efficient locomotion. Deep reinforcement learning (DRL) offers a promising framework for handling non-deterministic environments and enabling robotic systems to adapt effectively and perform robustly under challenging conditions. In this study, we comparatively examine learning-based control strategies and biologically inspired gait design methods on a salamander-like robot.