Hae-Won Park

Donghoon Youm, Hyunyoung Jung, Hyeongjun Kim et al.

Control of legged robots is a challenging problem that has been investigated by different approaches, such as model-based control and learning algorithms. This work proposes a novel Imitating and Finetuning Model Predictive Control (IFM) framework to take the strengths of both approaches. Our framework first develops a conventional model predictive controller (MPC) using Differential Dynamic Programming and Raibert heuristic, which serves as an expert policy. Then we train a clone of the MPC using imitation learning to make the controller learnable. Finally, we leverage deep reinforcement learning with limited exploration for further finetuning the policy on more challenging terrains. By conducting comprehensive simulation and hardware experiments, we demonstrate that the proposed IFM framework can significantly improve the performance of the given MPC controller on rough, slippery, and conveyor terrains that require careful coordination of footsteps. We also showcase that IFM can efficiently produce more symmetric, periodic, and energy-efficient gaits compared to Vanilla RL with a minimal burden of reward shaping.

Dongyun Kang, Min-Gyu Kim, Tae-Gyu Song et al.

Generating dynamic motions for legged robots remains a challenging problem. While reinforcement learning has achieved notable success in various legged locomotion tasks, producing highly dynamic behaviors often requires extensive reward tuning or high-quality demonstrations. Leveraging reduced-order models can help mitigate these challenges. However, the model discrepancy poses a significant challenge when transferring policies to full-body dynamics environments. In this work, we introduce a continuation-based learning framework that combines simplified model pretraining and model-homotopy-inspired transfer to efficiently generate and refine complex dynamic behaviors. First, we pretrain the policy using a single rigid body model to capture core motion patterns in a simplified environment. Next, we employ a continuation strategy to progressively transfer the policy to the full-body environment, minimizing performance loss. To define the continuation path, we introduce a parametric transition path from the single rigid body model to the full-body model by gradually redistributing mass and inertia between the trunk and legs. The proposed method achieves faster convergence and demonstrates superior stability during the transfer process compared to baseline methods. Our framework is validated on a range of dynamic tasks, including flips and wall-assisted maneuvers, and is successfully deployed on a real quadrupedal robot.

Sowoo Lee, Dongyun Kang, Jaehyun Park et al.

This paper introduces DynaFlow, a novel framework that embeds a differentiable simulator directly into a flow matching model. By generating trajectories in the action space and mapping them to dynamically feasible state trajectories via the simulator, DynaFlow ensures all outputs are physically consistent by construction. This end-to-end differentiable architecture enables training on state-only demonstrations, allowing the model to simultaneously generate physically consistent state trajectories while inferring the underlying action sequences required to produce them. We demonstrate the effectiveness of our approach through quantitative evaluations and showcase its real-world applicability by deploying the generated actions onto a physical Go1 quadruped robot. The robot successfully reproduces diverse gait present in the dataset, executes long-horizon motions in open-loop control and translates infeasible kinematic demonstrations into dynamically executable, stylistic behaviors. These hardware experiments validate that DynaFlow produces deployable, highly effective motions on real-world hardware from state-only demonstrations, effectively bridging the gap between kinematic data and real-world execution.

Yeeun Kim, Byeongho Yu, Eungchang Mason Lee et al.

We propose a novel state estimator for legged robots, STEP, achieved through a novel preintegrated foot velocity factor. In the preintegrated foot velocity factor, the usual non-slip assumption is not adopted. Instead, the end effector velocity becomes observable by exploiting the body speed obtained from a stereo camera. In other words, the preintegrated end effector's pose can be estimated. Another advantage of our approach is that it eliminates the necessity for a contact detection step, unlike the typical approaches. The proposed method has also been validated in harsh-environment simulations and real-world experiments containing uneven or slippery terrains.

Yanran Ding, Abhishek Pandala, Chuanzheng Li et al.

This paper presents a novel Representation-Free Model Predictive Control (RF-MPC) framework for controlling various dynamic motions of a quadrupedal robot in three dimensional (3D) space. Our formulation directly represents the rotational dynamics using the rotation matrix, which liberates us from the issues associated with the use of Euler angles and quaternion as the orientation representations. With a variation-based linearization scheme and a carefully constructed cost function, the MPC control law is transcribed to the standard Quadratic Program (QP) form. The MPC controller can operate at real-time rates of 250 Hz on a quadruped robot. Experimental results including periodic quadrupedal gaits and a controlled backflip validate that our control strategy could stabilize dynamic motions that involve singularity in 3D maneuvers.

Yanran Ding, Chuanzheng Li, Hae-Won Park

This paper proposes a kinodynamic motion planning framework for multi-legged robot jumping based on the mixed-integer convex program (MICP), which simultaneously reasons about centroidal motion, contact points, wrench, and gait sequences. This method uniquely combines configuration space discretization and the construction of feasible wrench polytope (FWP) to encode kinematic constraints, actuator limit, friction cone constraint, and gait sequencing into a single MICP. The MICP could be efficiently solved to the global optimum by off-the-shelf numerical solvers and provide highly dynamic jumping motions without requiring initial guesses. Simulation and experimental results demonstrate that the proposed method could find novel and dexterous maneuvers that are directly deployable on the two-legged robot platform to traverse through challenging terrains.