Bridging the sim-to-real gap remains a fundamental challenge in robotics, as accurate dynamic parameter estimation is essential for reliable model-based control, realistic simulation, and safe deployment of manipulators. Traditional analytical approaches often fall short when faced with complex robot structures and interactions. Data-driven methods offer a promising alternative, yet conventional neural networks such as recurrent models struggle to capture long-range dependencies critical for accurate estimation. In this study, we propose a Transformer-based approach for dynamic parameter estimation, supported by an automated pipeline that generates diverse robot models and enriched trajectory data using Jacobian-derived features. The dataset consists of 8,192 robots with varied inertial and frictional properties. Leveraging attention mechanisms, our model effectively captures both temporal and spatial dependencies. Experimental results highlight the influence of sequence length, sampling rate, and architecture, with the best configuration (sequence length 64, 64 Hz, four layers, 32 heads) achieving a validation R2 of 0.8633. Mass and inertia are estimated with near-perfect accuracy, Coulomb friction with moderate-to-high accuracy, while viscous friction and distal link center-of-mass remain more challenging. These results demonstrate that combining Transformers with automated dataset generation and kinematic enrichment enables scalable, accurate dynamic parameter estimation, contributing to improved sim-to-real transfer in robotic systems

Cross-domain transfer in robotic manipulation remains a longstanding challenge due to the significant domain gap between simulated and real-world environments. Existing methods such as domain randomization, adaptation, and sim-real calibration often require extensive tuning or fail to generalize to unseen scenarios. To address this issue, we observe that if domain-invariant features are utilized during policy training in simulation, and the same features can be extracted and provided as the input to policy during real-world deployment, the domain gap can be effectively bridged, leading to significantly improved policy generalization. Accordingly, we propose Semantic 2D Gaussian Splatting (S2GS), a novel representation method that extracts object-centric, domain-invariant spatial features. S2GS constructs multi-view 2D semantic fields and projects them into a unified 3D space via feature-level Gaussian splatting. A semantic filtering mechanism removes irrelevant background content, ensuring clean and consistent inputs for policy learning. To evaluate the effectiveness of S2GS, we adopt Diffusion Policy as the downstream learning algorithm and conduct experiments in the ManiSkill simulation environment, followed by real-world deployment. Results demonstrate that S2GS significantly improves sim-to-real transferability, maintaining high and stable task performance in real-world scenarios.

Human grasps can be roughly categorized into two types: power grasps and precision grasps. Precision grasping enables tool use and is believed to have influenced human evolution. Today's multi-fingered robotic hands are effective in power grasps, but for tasks requiring precision, parallel grippers are still more widely adopted. This contrast highlights a key limitation in current robotic hand design: the difficulty of achieving both stable power grasps and precise, fine-grained manipulation within a single, versatile system. In this work, we bridge this gap by jointly optimizing the control and hardware design of a multi-fingered dexterous hand, enabling both power and precision manipulation. Rather than redesigning the entire hand, we introduce a lightweight fingertip geometry modification, represent it as a contact plane, and jointly optimize its parameters along with the corresponding control. Our control strategy dynamically switches between power and precision manipulation and simplifies precision control into parallel thumb-index motions, which proves robust for sim-to-real transfer. On the design side, we leverage large-scale simulation to optimize the fingertip geometry using a differentiable neural-physics surrogate model. We validate our approach through extensive experiments in both sim-to-real and real-to-real settings. Our method achieves an 82.5% zero-shot success rate on unseen objects in sim-to-real precision grasping, and a 93.3% success rate in challenging real-world tasks involving bread pinching. These results demonstrate that our co-design framework can significantly enhance the fine-grained manipulation ability of multi-fingered hands without reducing their ability for power grasps. Our project page is at https://jianglongye.com/power-to-precision

The human-like form of humanoid robots positions them uniquely to achieve the agility and versatility in motor skills that humans possess. Learning from human demonstrations offers a scalable approach to acquiring these capabilities. However, prior works either produce unnatural motions or rely on motion-specific tuning to achieve satisfactory naturalness. Furthermore, these methods are often motion- or goal-specific, lacking the versatility to compose diverse skills, especially when solving unseen tasks. We present BeyondMimic, a framework that scales to diverse motions and carries the versatility to compose them seamlessly in tackling unseen downstream tasks. At heart, a compact motion-tracking formulation enables mastering a wide range of radically agile behaviors, including aerial cartwheels, spin-kicks, flip-kicks, and sprinting, with a single setup and shared hyperparameters, all while achieving state-of-the-art human-like performance. Moving beyond the mere imitation of existing motions, we propose a unified latent diffusion model that empowers versatile goal specification, seamless task switching, and dynamic composition of these agile behaviors. Leveraging classifier guidance, a diffusion-specific technique for test-time optimization toward novel objectives, our model extends its capability to solve downstream tasks never encountered during training, including motion inpainting, joystick teleoperation, and obstacle avoidance, and transfers these skills zero-shot to real hardware. This work opens new frontiers for humanoid robots by pushing the limits of scalable human-like motor skill acquisition from human motion and advancing seamless motion synthesis that achieves generalization and versatility beyond training setups.

Reinforcement learning (RL) has shown promise in robotics, but deploying RL on real vehicles remains challenging due to the complexity of vehicle dynamics and the mismatch between simulation and reality. Factors such as tire characteristics, road surface conditions, aerodynamic disturbances, and vehicle load make it infeasible to model real-world dynamics accurately, which hinders direct transfer of RL agents trained in simulation. In this paper, we present a framework that decouples motion planning from vehicle control through a spatial and temporal alignment strategy between a virtual vehicle and the real system. An RL agent is first trained in simulation using a kinematic bicycle model to output continuous control actions. Its behavior is then distilled into a trajectory-predicting agent that generates finite-horizon ego-vehicle trajectories, enabling synchronization between virtual and real vehicles. At deployment, a Stanley controller governs lateral dynamics, while longitudinal alignment is maintained through adaptive update mechanisms that compensate for deviations between virtual and real trajectories. We validate our approach on a real vehicle and demonstrate that the proposed alignment strategy enables robust zero-shot transfer of RL-based motion planning from simulation to reality, successfully decoupling high-level trajectory generation from low-level vehicle control.

Abstract--This chapter addresses the critical challenge of simulation-to-reality (sim-to-real) transfer for deep reinforcement learning (DRL) in bipedal locomotion. The first is to shrink the gap through model-centric strategies that systematically improve the simulator's physical fidelity. The second is to harden the policy, a complementary approach that uses in-simulation robustness training and post-deployment adaptation to make the policy inherently resilient to model inaccuracies. The chapter concludes by synthesizing these philosophies into a strategic framework, providing a clear roadmap for developing and evaluating robust sim-to-real solutions. Bipedal robots, machines that walk on two legs, are compelling platforms for operation in human-centric and natural environments. They can climb stairs, step over irregular obstacles, traverse narrow passages, and access spaces that are impractical for wheeled platforms. Their anthropomorphic form factor also enables natural interaction with tools and infrastructure designed for humans, making them suitable for disaster response, healthcare, logistics, and industrial applications. Bipedal locomotion remains challenging because of its high dimensionality, underactuation, and intermittent contacts. Model-based methods struggle with complex dynamics, whereas deep reinforcement learning (DRL) has achieved impressive simulation results in bipedal locomotion through trial and error. As shown in Figure 1, DRL achieves more robust performance than model-based control, particularly as task complexity increases. Most controllers adopt either end-to-end policies that map observations to actions or hierarchical policies that decouple high-level (HL) intent from low-level (LL) execution. Both approaches perform well in simulation but transfer unreliably to hardware, a limitation known as the sim-to-real gap.

Sim-to-real transfer remains a major challenge in reinforcement learning (RL) for robotics, as policies trained in simulation often fail to generalize to the real world due to discrepancies in environment dynamics. While standard approaches typically train policies agnostic to these variations, we investigate whether sim-to-real transfer can be improved by conditioning the policy on an estimate of the dynamics parameters -- referred to as context. To this end, we integrate a context estimation module into a DR-based RL framework and systematically compare SOTA supervision strategies. We evaluate the resulting context-aware policies in both a canonical control benchmark and a real-world pushing task using a Franka Emika Panda robot. Results show that context-aware policies outperform the context-agnostic baseline across all settings, although the best supervision strategy depends on the task. Introduction Reinforcement learning (RL) has achieved significant success in developing robot controllers capable of solving complex tasks [1]. To address these limitations, physics simulation engines are widely used as a safer and more efficient alternative for policy training. Once a policy has been trained in simulation, it is transferred to the physical robot--a process known as sim-to-real transfer [2, 1, 3]. Although promising, this paradigm is hindered by the reality or sim-to-real gap, which refers to the discrepancy between the simulated and real-world environments [4, 5].

Deploying reinforcement learning (RL) safely in the real world is challenging, as policies trained in simulators must face the inevitable sim-to-real gap. Robust safe RL techniques are provably safe, however difficult to scale, while domain randomization is more practical yet prone to unsafe behaviors. We address this gap by proposing SPiDR, short for Sim-to-real via Pessimistic Domain Randomization -- a scalable algorithm with provable guarantees for safe sim-to-real transfer. SPiDR uses domain randomization to incorporate the uncertainty about the sim-to-real gap into the safety constraints, making it versatile and highly compatible with existing training pipelines. Through extensive experiments on sim-to-sim benchmarks and two distinct real-world robotic platforms, we demonstrate that SPiDR effectively ensures safety despite the sim-to-real gap while maintaining strong performance.

Autonomous drone racing (ADR) systems have recently achieved champion-level performance, yet remain highly specific to drone racing. While end-to-end vision-based methods promise broader applicability, no system to date simultaneously achieves full sim-to-real transfer, onboard execution, and champion-level performance. In this work, we present SkyDreamer, to the best of our knowledge, the first end-to-end vision-based ADR policy that maps directly from pixel-level representations to motor commands. SkyDreamer builds on informed Dreamer, a model-based reinforcement learning approach where the world model decodes to privileged information only available during training. By extending this concept to end-to-end vision-based ADR, the world model effectively functions as an implicit state and parameter estimator, greatly improving interpretability. SkyDreamer runs fully onboard without external aid, resolves visual ambiguities by tracking progress using the state decoded from the world model's hidden state, and requires no extrinsic camera calibration, enabling rapid deployment across different drones without retraining. Real-world experiments show that SkyDreamer achieves robust, high-speed flight, executing tight maneuvers such as an inverted loop, a split-S and a ladder, reaching speeds of up to 21 m/s and accelerations of up to 6 g. It further demonstrates a non-trivial visual sim-to-real transfer by operating on poor-quality segmentation masks, and exhibits robustness to battery depletion by accurately estimating the maximum attainable motor RPM and adjusting its flight path in real-time. These results highlight SkyDreamer's adaptability to important aspects of the reality gap, bringing robustness while still achieving extremely high-speed, agile flight.