Dongchen Liu

Kuan Zhang, Dongchen Liu, Qiyue Zhao et al.

The real world unfolds along a single set of physics laws, yet human intelligence demonstrates a remarkable capacity to generalize experiences from this singular physical existence into a multiverse of games, each governed by entirely different rules, aesthetics, physics, and objectives. This omni-reality adaptability is a hallmark of general intelligence. As Artificial Intelligence progresses towards Artificial General Intelligence, the multiverse of games has evolved from mere entertainment into the ultimate ground for training and evaluating AGI. The pursuit of this generality has unfolded across four eras: from environment-specific symbolic and reinforcement learning agents, to current large foundation models acting as generalist players, and toward a future creator stage where agent both creates new game worlds and continually evolves within them. We trace the full lifecycle of a generalist game player along four interdependent pillars: Dataset, Model, Harness, and Benchmark. Every advance across these pillars can be read as an attempt to break one of five fundamental trade-offs that currently bound the whole system. Building on this end-to-end view, we chart a five-level roadmap, progressing from single-game mastery to the ultimate creator stage in which the agent simultaneously creates and evolves within theoretical game multiverse. Taken together, our work offers a unified lens onto a rapidly shifting field,and a principled path toward the omnipotent generalist agent capable of seamlessly mastering any challenge within the multiverse of games, thereby paving the way for AGI.

Dongchen Liu, Junzheng Wang, Shoukun Wang

This work presents the coordinated motion control and obstacle-crossing problem for the four wheel-leg independent motor-driven robotic systems via a model predictive control (MPC) approach based on an event-triggering mechanism. The modeling of a wheel-leg robotic control system with a dynamic supporting polygon is organized. The system dynamic model is 3 degrees of freedom (DOF) ignoring the pitch, roll and vertical motions. The single wheel dynamic is analyzed considering the characteristics of motor-driven and the Burckhardt nonlinear tire model. As a result, an over-actuated predictive model is proposed with the motor torques as inputs and the system states as outputs. As the supporting polygon is only adjusted at certain conditions, an event-based triggering mechanism is designed to save hardware resources and energy. The MPC controller is evaluated on a virtual prototype as well as a physical prototype. The simulation results guide the parameter tuning for the controller implementation in the physical prototype. The experimental results on these two prototypes verify the efficiency of the proposed approach.

Dongchen Liu, Junzheng Wang, Shoukun Wang et al.

This work proposes a force control strategy with prescribed transient performance for the legs of a wheel-legged robotic system to realize the posture adjustment on uneven roads. A dynamic model of the robotic system is established with the body postures as inputs and the leg forces as outputs, such that the desired forces for the wheel-legs are calculated by the posture reference and feedback. Based on the funnel control scheme, the legs realize force tracking with prescribed transient performance. To improve the robustness of the force control system, an event-based mechanism is designed for the online segment of the funnel function. As a result, the force tracking error of the wheel-leg evolves inside the performance funnel with proved convergence. The absence of Zeno behavior for the event-triggering condition is also guaranteed. The proposed control scheme is applied to the wheel-legged physical prototype for the performance of force tracking and posture adjustment. Multiple comparative experimental results are presented to validate the stability and effectiveness of the proposed methodology.