Search for: All records

This paper presents a comprehensive study on using deep reinforcement learning (RL) to create dynamic locomotion controllers for bipedal robots. Going beyond focusing on a single locomotion skill, we develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing. Our RL-based controller incorporates a novel dual-history architecture, utilizing both a long-term and short-term input/output (I/O) history of the robot. This control architecture, when trained through the proposed end-to-end RL approach, consistently outperforms other methods across a diverse range of skills in both simulation and the real world. The study also delves into the adaptivity and robustness introduced by the proposed RL system in developing locomotion controllers. We demonstrate that the proposed architecture can adapt to both time-invariant dynamics shifts and time-variant changes, such as contact events, by effectively using the robot’s I/O history. Additionally, we identify task randomization as another key source of robustness, fostering better task generalization and compliance to disturbances. The resulting control policies can be successfully deployed on Cassie, a torque-controlled human-sized bipedal robot. This work pushes the limits of agility for bipedal robots through extensive real-world experiments. We demonstrate a diverse range of locomotion skills, including: robust standing, versatile walking, fast running with a demonstration of a 400-meter dash, and a diverse set of jumping skills, such as standing long jumps and high jumps. 

Abstract Synergistically improving T-cell responsiveness is promising for favorable therapeutic outcomes in immunologically cold tumors, yet current treatments often fail to induce a cascade of cancer-immunity cycle for effective antitumor immunity. Gasdermin-mediated pyroptosis is a newly discovered mechanism in cancer immunotherapy; however, cleavage in the N terminus is required to activate pyroptosis. Here, we report a single-agent mRNA nanomedicine-based strategy that utilizes mRNA lipid nanoparticles (LNPs) encoding only the N-terminus of gasdermin to trigger pyroptosis, eliciting robust antitumor immunity. In multiple female mouse models, we show that pyroptosis-triggering mRNA/LNPs turn cold tumors into hot ones and create a positive feedback loop to promote antitumor immunity. Additionally, mRNA/LNP-induced pyroptosis sensitizes tumors to anti-PD-1 immunotherapy, facilitating tumor growth inhibition. Antitumor activity extends beyond the treated lesions and suppresses the growth of distant tumors. We implement a strategy for inducing potent antitumor immunity, enhancing immunotherapy responses in immunologically cold tumors.