We consider the problem of policy transfer between two Markov Decision Processes (MDPs). We introduce a lemma based on existing theoretical results in reinforcement learning to measure the relativity gap between two arbitrary MDPs, that is the difference between any two cumulative expected returns defined on different policies and environment dynamics. Based on this lemma, we propose two new algorithms referred to as Relative Policy Optimization (RPO) and Relative Transition Optimization (RTO), which offer fast policy transfer and dynamics modelling, respectively. RPO transfers the policy evaluated in one environment to maximize the return in another, while RTO updates the parameterized dynamics model to reduce the gap between the dynamics of the two environments. Integrating the two algorithms results in the complete Relative Policy-Transition Optimization (RPTO) algorithm, in which the policy interacts with the two environments simultaneously, such that data collections from two environments, policy and transition updates are completed in one closed loop to form a principled learning framework for policy transfer. We demonstrate the effectiveness of RPTO on a set of MuJoCo continuous control tasks by creating policy transfer problems via variant dynamics.

Learning highly dynamic behaviors for robots has been a longstanding challenge. Traditional approaches have demonstrated robust locomotion, but the exhibited behaviors lack diversity and agility. They employ approximate models, which lead to compromises in performance. Data-driven approaches have been shown to reproduce agile behaviors of animals, but typically have not been able to learn highly dynamic behaviors. In this paper, we propose a learning-based approach to enable robots to learn highly dynamic behaviors from animal motion data. The learned controller is deployed on a quadrupedal robot and the results show that the controller is able to reproduce highly dynamic behaviors including sprinting, jumping and sharp turning. Various behaviors can be activated through human interaction using a stick with markers attached to it. Based on the motion pattern of the stick, the robot exhibits walking, running, sitting and jumping, much like the way humans interact with a pet.

Physical Human-Scene Interaction (HSI) plays a crucial role in numerous applications. However, existing HSI techniques are limited to specific object dynamics and privileged information, which prevents the development of more comprehensive applications. To address this limitation, we introduce HumanVLA for general object rearrangement directed by practical vision and language. A teacher-student framework is utilized to develop HumanVLA. A state-based teacher policy is trained first using goal-conditioned reinforcement learning and adversarial motion prior. Then, it is distilled into a vision-language-action model via behavior cloning. We propose several key insights to facilitate the large-scale learning process. To support general object rearrangement by physical humanoid, we introduce a novel Human-in-the-Room dataset encompassing various rearrangement tasks. Through extensive experiments and analysis, we demonstrate the effectiveness of our approach.

Accurate measuring and modeling of dynamic robot manipulation (e.g., tossing and catching) is particularly challenging, due to the inherent nonlinearity, complexity, and uncertainty in high-speed robot motions and highly dynamic robot–object interactions happening in very short distances and times. Most studies leverage extrinsic sensors such as visual and tactile feedback toward task or object-centric modeling of manipulation dynamics, which, however, may hit bottleneck due to the significant cost and complexity, e.g., the environmental restrictions. In this work, we investigate whether using solely the on-board proprioceptive sensory modalities can effectively capture and characterize dynamic manipulation processes. In particular, we present an object-agnostic strategy to learn the robot toss dynamics of arbitrary unknown objects from the spatio-temporal variations of robot toss movements and wrist-force/torque (F/T) observations. We then propose TossNet, an end-to-end formulation that jointly measures the robot toss dynamics and predicts the resulting flying trajectories of the tossed objects. Experimental results in both simulation and real-world scenarios demonstrate that our methods can accurately model the robot toss dynamics of both seen and unseen objects, and predict their flying trajectories with superior prediction accuracy in nearly real-time. Ablative results are also presented to demonstrate the effectiveness of each proprioceptive modality and their correlations in modeling the toss dynamics. Case studies show that TossNet can be applied on various real robot platforms for challenging tossing-centric robot applications, such as blind juggling and high-precise robot pitching.

In this paper, we present a general learning framework for controlling a quadruped robot that can mimic the behavior of real animals and traverse challenging terrains. Our method consists of two steps: an imitation learning step to learn from motions of real animals, and a terrain adaptation step to enable generalization to unseen terrains. We capture motions from a Labrador on various terrains to facilitate terrain adaptive locomotion. Our experiments demonstrate that our policy can traverse various terrains and produce a natural-looking behavior. We deployed our method on the real quadruped robot$\boldsymbol{Max}$[1] via zero-shot simulation-to-reality transfer, achieving a speed of 1.1 m/s on stairs climbing.

This research presents a novel Collective Robotic Construction (CRC) system named RECCraft. The RECCraft hardware system is composed of the mobile manipulation vehicles, the cubic blocks, and the folding ramp blocks. Solid connection and easy removal of the blocks are achieved by an electropermanent magnet and silicon steel sheets. With one degree of freedom (DOF) lifting manipulator, the robot can carry a block 3.7 times its volume. An active folding ramp block can provide a robust passage to the upper level for the robot. Our study focuses on systemic improvement of the construction speed and reliability of the robotic construction system. Visual perception system realized by Apritag is adopted, featured by convenient deployment and high precision, to provide a reliable guarantee for robotic construction. RL-based planner provides end-to-end solution for planning tasks of building multi-layer constructions, which is validated by simulation platform and real prototype. Compared with construction speed of existing robotic construction systems, our proposed RECCraft system achieves state-of-the-art level. The robot builds a 2-layer construction by RL-based planner in 4 minutes and 16 seconds, which achieves construction volumetric throughput of 6.7×105mm3/s.