arXiv subjects

Nicolas Mansard

Publications and source records attributed to Nicolas Mansard.

At least 19 recordsLinked to original sources

arXiv2026

CAST: Alternating State-Value Targets and Expanded Policy Gradients for Model-Based Reinforcement Learning

Model-based reinforcement learning (MBRL) is a family of RL methods that learn a model of the environment and use it for action selection, making it well suited to robotics due to its sample efficiency. Combining learned models with online planning can further improve action selection, as the planner can exploit the model to find better actions than the learned policy alone. Recent methods combining learned policies with online planning typically learn the value of the policy rather than the stronger planner-guided behavior. We present CAST (Critic with Alternating State-value Target), which uses planner-guided behavior to improve value learning while regularizing the value estimate with the current policy. CAST replaces the action-value critic with a state-value critic, trained using a target that combines a real planner-guided transition and an imagined transition under the current policy. The resulting value function corresponds to an alternating process between planner-guided behavior and the current policy, allowing it to benefit from the stronger planner behavior while being regularised by the policy being learned. We evaluate CAST on the DeepMind Control and HumanoidBench Suites against several state-of-the-art methods, and demonstrate successful transfer to a physical Unitree Go2 quadruped performing a dynamic handstand.

cs.RO↗

arXiv2026

Direct Dynamic Retargeting for Humanoid Imitation Learning from Videos

Imitation Learning from monocular video demonstrations provides a scalable approach for teaching complex skills to humanoid robots. However, translating human motion to humanoids requires overcoming significant morphological mismatches. Standard approaches rely on Geometric Retargeting or Indirect Dynamic Retargeting pipelines. We identify that these intermediate kinematic projections introduce a geometric bias, restricting the search space and yielding suboptimal dynamic behaviors. In this paper, we propose Direct Dynamic Retargeting (DDR), a novel single-stage framework that generates high-fidelity, dynamically feasible trajectories directly from expert videos. By formulating the problem in the task space and leveraging a sampling-based Model Predictive Control solver within a physics simulator, DDR natively optimizes over complex contact sequences while mitigating input drift. Our experiments demonstrate that bypassing the geometric bias allows DDR to outperform state-of-the-art baselines in demonstration tracking accuracy. Furthermore, we establish that providing such physically viable references to RL agents accelerates training convergence and enhances the final execution of agile and balancing behaviors. Source code will be made publicly available.

cs.RO↗

arXiv2026

COSMIK-MPPI: Scaling Constrained Model Predictive Control to Collision Avoidance in Close-Proximity Dynamic Human Environments

Ensuring safe physical interaction between torque-controlled manipulators and humans is essential for deploying robots in everyday environments. Model Predictive Control (MPC) has emerged as a suitable framework thanks to its capacity to handle hard constraints, provide strong guarantees and zero-shot adaptability through predictive reasoning. However, Gradient-Based MPC (GB-MPC) solvers have demonstrated limited performance for collision avoidance in complex environments. Sampling-based approaches such as Model Predictive Path Integral (MPPI) control offer an alternative via stochastic rollouts, but enforcing safety via additive penalties is inherently fragile, as it provides no formal constraint satisfaction guarantees. We propose a collision avoidance framework called COSMIK-MPPI combining MPPI with the toolbox for human motion estimation RT-COSMIK and the Constraints-as-Terminations transcription, which enforces safety by treating constraint violations as terminal events, without relying on large penalty terms or explicit human motion prediction. The proposed approach is evaluated against state-of-the-art GB-MPC and vanilla MPPI in simulation and on a real manipulator arm. Results show that COSMIK-MPPI achieves a 100% task success rate with a constant computation time (22 ms), largely outperforming GB-MPC. In simulated infeasible scenarios, COSMIK-MPPI consistently generates collision-free trajectories, contrary to vanilla MPPI. These properties enabled safe execution of complex real-world human-robot interaction tasks in shared workspaces using an affordable markerless human motion estimator, demonstrating a robust, compliant, and practical solution for predictive collision avoidance (cf. results showcased at https://exquisite-parfait-ffa925.netlify.app)

cs.RO↗

arXiv2026

Learning-Guided Force-Feedback Model Predictive Control with Obstacle Avoidance for Robotic Deburring

Model Predictive Control (MPC) is widely used for torque-controlled robots, but classical formulations often neglect real-time force feedback and struggle with contact-rich industrial tasks under collision constraints. Deburring in particular requires precise tool insertion, stable force regulation, and collision-free circular motions in challenging configurations, which exceeds the capability of standard MPC pipelines. We propose a framework that integrates force-feedback MPC with diffusion-based motion priors to address these challenges. The diffusion model serves as a memory of motion strategies, providing robust initialization and adaptation across multiple task instances, while MPC ensures safe execution with explicit force tracking, torque feasibility, and collision avoidance. We validate our approach on a torque-controlled manipulator performing industrial deburring tasks. Experiments demonstrate reliable tool insertion, accurate normal force tracking, and circular deburring motions even in hard-to-reach configurations and under obstacle constraints. To our knowledge, this is the first integration of diffusion motion priors with force-feedback MPC for collision-aware, contact-rich industrial tasks.

cs.RO↗

arXiv2026

Coupled Local and Global World Models for Efficient First Order RL

World models offer a promising avenue for more faithfully capturing complex dynamics, including contacts and non-rigidity, as well as complex sensory information, such as visual perception, in situations where standard simulators struggle. However, these models are computationally complex to evaluate, posing a challenge for popular RL approaches that have been successfully used with simulators to solve complex locomotion tasks but yet struggle with manipulation. This paper introduces a method that bypasses simulators entirely, training RL policies inside world models learned from robots' interactions with real environments. At its core, our approach enables policy training with large-scale diffusion models via a novel decoupled first-order gradient (FoG) method: a full-scale world model generates accurate forward trajectories, while a lightweight latent-space surrogate approximates its local dynamics for efficient gradient computation. This coupling of a local and global world model ensures high-fidelity unrolling alongside computationally tractable differentiation. We demonstrate the efficacy of our method on the Push-T manipulation task, where it significantly outperforms PPO in sample efficiency. We further evaluate our approach through an ego-centric object manipulation task with a quadruped. Together, these results demonstrate that learning inside data-driven world models is a promising pathway for solving hard-to-model RL tasks in image space without reliance on hand-crafted physics simulators.

cs.RO↗

arXiv2026

Warm-Starting Collision-Free Model Predictive Control With Object-Centric Diffusion

Acting in cluttered environments requires predicting and avoiding collisions while still achieving precise control. Conventional optimization-based controllers can enforce physical constraints, but they struggle to produce feasible solutions quickly when many obstacles are present. Diffusion models can generate diverse trajectories around obstacles, yet prior approaches lacked a general and efficient way to condition them on scene structure. In this paper, we show that combining diffusion-based warm-starting conditioned with a latent object-centric representation of the scene and with a collision-aware model predictive controller (MPC) yields reliable and efficient motion generation under strict time limits. Our approach conditions a diffusion transformer on the system state, task, and surroundings, using an object-centric slot attention mechanism to provide a compact obstacle representation suitable for control. The sampled trajectories are refined by an optimal control problem that enforces rigid-body dynamics and signed-distance collision constraints, producing feasible motions in real time. On benchmark tasks, this hybrid method achieved markedly higher success rates and lower latency than sampling-based planners or either component alone. Real-robot experiments with a torque-controlled Panda confirm reliable and safe execution with MPC.

cs.RO↗

arXiv2025

Very High Frequency Interpolation for Direct Torque Control

Torque control enables agile and robust robot motion, but deployment is often hindered by instability and hardware limits. Here, we present a novel solution to execute whole-body linear feedback at up to 40 kHz on open-source hardware. We use this to interpolate non-linear schemes during real-world execution, such as inverse dynamics and learned torque policies. Our results show that by stabilizing torque controllers, high-frequency linear feedback could be an effective route towards unlocking the potential of torque-controlled robotics.

cs.RO↗

arXiv2025

First Order Model-Based RL through Decoupled Backpropagation

There is growing interest in reinforcement learning (RL) methods that leverage the simulator's derivatives to improve learning efficiency. While early gradient-based approaches have demonstrated superior performance compared to derivative-free methods, accessing simulator gradients is often impractical due to their implementation cost or unavailability. Model-based RL (MBRL) can approximate these gradients via learned dynamics models, but the solver efficiency suffers from compounding prediction errors during training rollouts, which can degrade policy performance. We propose an approach that decouples trajectory generation from gradient computation: trajectories are unrolled using a simulator, while gradients are computed via backpropagation through a learned differentiable model of the simulator. This hybrid design enables efficient and consistent first-order policy optimization, even when simulator gradients are unavailable, as well as learning a critic from simulation rollouts, which is more accurate. Our method achieves the sample efficiency and speed of specialized optimizers such as SHAC, while maintaining the generality of standard approaches like PPO and avoiding ill behaviors observed in other first-order MBRL methods. We empirically validate our algorithm on benchmark control tasks and demonstrate its effectiveness on a real Go2 quadruped robot, across both quadrupedal and bipedal locomotion tasks.

cs.RO↗

arXiv2025

Multi-step manipulation task and motion planning guided by video demonstration

This work aims to leverage instructional video to solve complex multi-step task-and-motion planning tasks in robotics. Towards this goal, we propose an extension of the well-established Rapidly-Exploring Random Tree (RRT) planner, which simultaneously grows multiple trees around grasp and release states extracted from the guiding video. Our key novelty lies in combining contact states and 3D object poses extracted from the guiding video with a traditional planning algorithm that allows us to solve tasks with sequential dependencies, for example, if an object needs to be placed at a specific location to be grasped later. We also investigate the generalization capabilities of our approach to go beyond the scene depicted in the instructional video. To demonstrate the benefits of the proposed video-guided planning approach, we design a new benchmark with three challenging tasks: (I) 3D re-arrangement of multiple objects between a table and a shelf, (ii) multi-step transfer of an object through a tunnel, and (iii) transferring objects using a tray similar to a waiter transfers dishes. We demonstrate the effectiveness of our planning algorithm on several robots, including the Franka Emika Panda and the KUKA KMR iiwa. For a seamless transfer of the obtained plans to the real robot, we develop a trajectory refinement approach formulated as an optimal control problem (OCP).

cs.RO↗

arXiv2025

Extended URDF: Accounting for parallel mechanism in robot description

Robotic designs played an important role in recent advances by providing powerful robots with complex mechanics. Many recent systems rely on parallel actuation to provide lighter limbs and allow more complex motion. However, these emerging architectures fall outside the scope of most used description formats, leading to difficulties when designing, storing, and sharing the models of these systems. This paper introduces an extension to the widely used Unified Robot Description Format (URDF) to support closed-loop kinematic structures. Our approach relies on augmenting URDF with minimal additional information to allow more efficient modeling of complex robotic systems while maintaining compatibility with existing design and simulation frameworks. This method sets the basic requirement for a description format to handle parallel mechanisms efficiently. We demonstrate the applicability of our approach by providing an open-source collection of parallel robots, along with tools for generating and parsing this extended description format. The proposed extension simplifies robot modeling, reduces redundancy, and improves usability for advanced robotic applications.

cs.RO↗

arXiv2025

Optimal Control of Walkers with Parallel Actuation

Legged robots with closed-loop kinematic chains are increasingly prevalent due to their increased mobility and efficiency. Yet, most motion generation methods rely on serial-chain approximations, sidestepping their specific constraints and dynamics. This leads to suboptimal motions and limits the adaptability of these methods to diverse kinematic structures. We propose a comprehensive motion generation method that explicitly incorporates closed-loop kinematics and their associated constraints in an optimal control problem, integrating kinematic closure conditions and their analytical derivatives. This allows the solver to leverage the non-linear transmission effects inherent to closed-chain mechanisms, reducing peak actuator efforts and expanding their effective operating range. Unlike previous methods, our framework does not require serial approximations, enabling more accurate and efficient motion strategies. We also are able to generate the motion of more complex robots for which an approximate serial chain does not exist. We validate our approach through simulations and experiments, demonstrating superior performance in complex tasks such as rapid locomotion and stair negotiation. This method enhances the capabilities of current closed-loop robots and broadens the design space for future kinematic architectures.

cs.RO↗

arXiv2025

Control of Humanoid Robots with Parallel Mechanisms using Differential Actuation Models

Several recently released humanoid robots, inspired by the mechanical design of Cassie, employ actuator configurations in which the motors are displaced from the joints to reduce leg inertia. While studies accounting for the full kinematic complexity have demonstrated the benefits of these designs, the associated loop-closure constraints greatly increase computational cost and limit their use in control and learning. As a result, the non-linear transmission is often approximated by a constant reduction ratio, preventing exploitation of the mechanism's full capabilities. This paper introduces a compact analytical formulation for the two standard knee and ankle mechanisms that captures the exact non-linear transmission while remaining computationally efficient. The model is fully differentiable up to second order with a minimal formulation, enabling low-cost evaluation of dynamic derivatives for trajectory optimization and of the apparent transmission impedance for reinforcement learning. We integrate this formulation into trajectory optimization and locomotion policy learning, and compare it against simplified constant-ratio approaches. Hardware experiments demonstrate improved accuracy and robustness, showing that the proposed method provides a practical means to incorporate parallel actuation into modern control algorithms.

cs.RO↗

arXiv2025

Infinite-Horizon Value Function Approximation for Model Predictive Control

Model Predictive Control has emerged as a popular tool for robots to generate complex motions. However, the real-time requirement has limited the use of hard constraints and large preview horizons, which are necessary to ensure safety and stability. In practice, practitioners have to carefully design cost functions that can imitate an infinite horizon formulation, which is tedious and often results in local minima. In this work, we study how to approximate the infinite horizon value function of constrained optimal control problems with neural networks using value iteration and trajectory optimization. Furthermore, we experimentally demonstrate how using this value function approximation as a terminal cost provides global stability to the model predictive controller. The approach is validated on two toy problems and a real-world scenario with online obstacle avoidance on an industrial manipulator where the value function is conditioned to the goal and obstacle.

cs.RO↗

arXiv2024

Reinforcement Learning from Wild Animal Videos

We propose to learn legged robot locomotion skills by watching thousands of wild animal videos from the internet, such as those featured in nature documentaries. Indeed, such videos offer a rich and diverse collection of plausible motion examples, which could inform how robots should move. To achieve this, we introduce Reinforcement Learning from Wild Animal Videos (RLWAV), a method to ground these motions into physical robots. We first train a video classifier on a large-scale animal video dataset to recognize actions from RGB clips of animals in their natural habitats. We then train a multi-skill policy to control a robot in a physics simulator, using the classification score of a third-person camera capturing videos of the robot's movements as a reward for reinforcement learning. Finally, we directly transfer the learned policy to a real quadruped Solo. Remarkably, despite the extreme gap in both domain and embodiment between animals in the wild and robots, our approach enables the policy to learn diverse skills such as walking, jumping, and keeping still, without relying on reference trajectories nor skill-specific rewards.

cs.RO↗

arXiv2024

SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience

Parkour poses a significant challenge for legged robots, requiring navigation through complex environments with agility and precision based on limited sensory inputs. In this work, we introduce a novel method for training end-to-end visual policies, from depth pixels to robot control commands, to achieve agile and safe quadruped locomotion. We formulate robot parkour as a constrained reinforcement learning (RL) problem designed to maximize the emergence of agile skills within the robot's physical limits while ensuring safety. We first train a policy without vision using privileged information about the robot's surroundings. We then generate experience from this privileged policy to warm-start a sample efficient off-policy RL algorithm from depth images. This allows the robot to adapt behaviors from this privileged experience to visual locomotion while circumventing the high computational costs of RL directly from pixels. We demonstrate the effectiveness of our method on a real Solo-12 robot, showcasing its capability to perform a variety of parkour skills such as walking, climbing, leaping, and crawling.

cs.RO↗

arXiv2024

Parallel and Proximal Constrained Linear-Quadratic Methods for Real-Time Nonlinear MPC

Recent strides in nonlinear model predictive control (NMPC) underscore a dependence on numerical advancements to efficiently and accurately solve large-scale problems. Given the substantial number of variables characterizing typical whole-body optimal control (OC) problems - often numbering in the thousands - exploiting the sparse structure of the numerical problem becomes crucial to meet computational demands, typically in the range of a few milliseconds. Addressing the linear-quadratic regulator (LQR) problem is a fundamental building block for computing Newton or Sequential Quadratic Programming (SQP) steps in direct optimal control methods. This paper concentrates on equality-constrained problems featuring implicit system dynamics and dual regularization, a characteristic of advanced interiorpoint or augmented Lagrangian solvers. Here, we introduce a parallel algorithm for solving an LQR problem with dual regularization. Leveraging a rewriting of the LQR recursion through block elimination, we first enhanced the efficiency of the serial algorithm and then subsequently generalized it to handle parametric problems. This extension enables us to split decision variables and solve multiple subproblems concurrently. Our algorithm is implemented in our nonlinear numerical optimal control library ALIGATOR. It showcases improved performance over previous serial formulations and we validate its efficacy by deploying it in the model predictive control of a real quadruped robot.

cs.RO↗

arXiv2024

CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning

Deep Reinforcement Learning (RL) has demonstrated impressive results in solving complex robotic tasks such as quadruped locomotion. Yet, current solvers fail to produce efficient policies respecting hard constraints. In this work, we advocate for integrating constraints into robot learning and present Constraints as Terminations (CaT), a novel constrained RL algorithm. Departing from classical constrained RL formulations, we reformulate constraints through stochastic terminations during policy learning: any violation of a constraint triggers a probability of terminating potential future rewards the RL agent could attain. We propose an algorithmic approach to this formulation, by minimally modifying widely used off-the-shelf RL algorithms in robot learning (such as Proximal Policy Optimization). Our approach leads to excellent constraint adherence without introducing undue complexity and computational overhead, thus mitigating barriers to broader adoption. Through empirical evaluation on the real quadruped robot Solo crossing challenging obstacles, we demonstrate that CaT provides a compelling solution for incorporating constraints into RL frameworks. Videos and code are available at https://constraints-as-terminations.github.io.

cs.RO↗

arXiv2023

Visually Guided Model Predictive Robot Control via 6D Object Pose Localization and Tracking

The objective of this work is to enable manipulation tasks with respect to the 6D pose of a dynamically moving object using a camera mounted on a robot. Examples include maintaining a constant relative 6D pose of the robot arm with respect to the object, grasping the dynamically moving object, or co-manipulating the object together with a human. Fast and accurate 6D pose estimation is crucial to achieve smooth and stable robot control in such situations. The contributions of this work are three fold. First, we propose a new visual perception module that asynchronously combines accurate learning-based 6D object pose localizer and a high-rate model-based 6D pose tracker. The outcome is a low-latency accurate and temporally consistent 6D object pose estimation from the input video stream at up to 120 Hz. Second, we develop a visually guided robot arm controller that combines the new visual perception module with a torque-based model predictive control algorithm. Asynchronous combination of the visual and robot proprioception signals at their corresponding frequencies results in stable and robust 6D object pose guided robot arm control. Third, we experimentally validate the proposed approach on a challenging 6D pose estimation benchmark and demonstrate 6D object pose-guided control with dynamically moving objects on a real 7 DoF Franka Emika Panda robot.

cs.RO↗