SLowRL: Safe Low-Rank Adaptation Reinforcement Learning for Locomotion

Sim-to-real transfer of locomotion policies often leads to performance degradation due to the inevitable sim-to-real gap. Naively fine-tuning these policies directly on hardware is problematic, as it poses risks of mechanical failure and suffers from high sample inefficiency. In this paper, we address the challenge of safely and efficiently fine-tuning reinforcement learning (RL) policies for dynamic locomotion tasks. Specifically, we focus on fine-tuning policies learned in simulation directly on hardware, while explicitly enforcing safety constraints. In doing so, we introduce SLowRL, a framework that combines Low-Rank Adaptation (LoRA) with training-time safety enforcement via a recovery policy. We evaluate our method both in simulation and on a real Unitree Go2 quadruped robot for jump and trot tasks. Experimental results show that our method achieves a $46.5\%$ reduction in fine-tuning time and near-zero safety violations compared to standard proximal policy optimization (PPO) baselines. Notably, we find that a rank-1 adaptation alone is sufficient to recover pre-trained performance in the real world, while maintaining stable and safe real-world fine-tuning. These results demonstrate the practicality of safe, efficient fine-tuning for dynamic real-world robotic applications.

DynaRetarget: Dynamically-Feasible Retargeting using Sampling-Based Trajectory Optimization

In this paper, we introduce DynaRetarget, a complete pipeline for retargeting human motions to humanoid control policies. The core component of DynaRetarget is a novel Sampling-Based Trajectory Optimization (SBTO) framework that refines imperfect kinematic trajectories into dynamically feasible motions. SBTO incrementally advances the optimization horizon, enabling optimization over the entire trajectory for long-horizon tasks. We validate DynaRetarget by successfully retargeting hundreds of humanoid-object demonstrations and achieving higher success rates than the state of the art. The framework also generalizes across varying object properties, such as mass, size, and geometry, using the same tracking objective. This ability to robustly retarget diverse demonstrations opens the door to generating large-scale synthetic datasets of humanoid loco-manipulation trajectories, addressing a major bottleneck in real-world data collection.

Fast Convex Visual Foothold Adaptation for Quadrupedal Locomotion

This extended abstract provides a short introduction on our recently developed perception-based controller for quadrupedal locomotion. Compared to our previous approach based on Visual Foothold Adaptation (VFA) and Model Predictive Control (MPC), our new framework combines a fast approximation of the safe foothold regions based on Neural Network regression, followed by a convex decomposition routine in order to generate safe landing areas where the controller can freely optimize the footholds location. The aforementioned framework, which combines prediction, convex decomposition, and MPC solution, is tested in simulation on our 140kg hydraulic quadruped robot (HyQReal).

SafeSteps: Learning Safer Footstep Planning Policies for Legged Robots via Model-Based Priors

We present a footstep planning policy for quadrupedal locomotion that is able to directly take into consideration a-priori safety information in its decisions. At its core, a learning process analyzes terrain patches, classifying each landing location by its kinematic feasibility, shin collision, and terrain roughness. This information is then encoded into a small vector representation and passed as an additional state to the footstep planning policy, which furthermore proposes only safe footstep location by applying a masked variant of the Proximal Policy Optimization (PPO) algorithm. The performance of the proposed approach is shown by comparative simulations on an electric quadruped robot walking in different rough terrain scenarios. We show that violations of the above safety conditions are greatly reduced both during training and the successive deployment of the policy, resulting in an inherently safer footstep planner. Furthermore, we show how, as a byproduct, fewer reward terms are needed to shape the behavior of the policy, which in return is able to achieve both better final performances and sample efficiency