This paper introduces the Safe Protective and Assistive Robot Kit (SPARK), a comprehensive benchmark designed to ensure safety in humanoid autonomy and teleoperation. Humanoid robots pose significant safety risks due to their physical capabilities of interacting with complex environments. The physical structures of humanoid robots further add complexity to the design of general safety solutions. To facilitate the safe deployment of complex robot systems, SPARK can be used as a toolbox that comes with state-of-the-art safe control algorithms in a modular and composable robot control framework. Users can easily configure safety criteria and sensitivity levels to optimize the balance between safety and performance. To accelerate humanoid safety research and development, SPARK provides a simulation benchmark that compares safety approaches in a variety of environments, tasks, and robot models. Furthermore, SPARK allows quick deployment of synthesized safe controllers on real robots. For hardware deployment, SPARK supports Apple Vision Pro (AVP) or a Motion Capture System as external sensors, while also offering interfaces for seamless integration with alternative hardware setups. This paper demonstrates SPARK's capability with both simulation experiments and case studies with a Unitree G1 humanoid robot. Leveraging these advantages of SPARK, users and researchers can significantly improve the safety of their humanoid systems as well as accelerate relevant research. The open-source code is available at https://github.com/intelligent-control-lab/spark.

The control of legged robots, particularly humanoid and quadruped robots, presents significant challenges due to their high-dimensional and nonlinear dynamics. While linear systems can be effectively controlled using methods like Model Predictive Control (MPC), the control of nonlinear systems remains complex. One promising solution is the Koopman Operator, which approximates nonlinear dynamics with a linear model, enabling the use of proven linear control techniques. However, achieving accurate linearization through data-driven methods is difficult due to issues like approximation error, domain shifts, and the limitations of fixed linear state-space representations. These challenges restrict the scalability of Koopman-based approaches. This paper addresses these challenges by proposing a continual learning algorithm designed to iteratively refine Koopman dynamics for high-dimensional legged robots. The key idea is to progressively expand the dataset and latent space dimension, enabling the learned Koopman dynamics to converge towards accurate approximations of the true system dynamics. Theoretical analysis shows that the linear approximation error of our method converges monotonically. Experimental results demonstrate that our method achieves high control performance on robots like Unitree G1/H1/A1/Go2 and ANYmal D, across various terrains using simple linear MPC controllers. This work is the first to successfully apply linearized Koopman dynamics for locomotion control of high-dimensional legged robots, enabling a scalable model-based control solution.

Enforcing state-wise safety constraints is critical for the application of reinforcement learning (RL) in real-world problems, such as autonomous driving and robot manipulation. However, existing safe RL methods only enforce state-wise constraints in expectation or enforce hard state-wise constraints with strong assumptions. The former does not exclude the probability of safety violations, while the latter is impractical. Our insight is that although it is intractable to guarantee hard state-wise constraints in a model-free setting, we can enforce state-wise safety with high probability while excluding strong assumptions. To accomplish the goal, we propose Absolute State-wise Constrained Policy Optimization (ASCPO), a novel general-purpose policy search algorithm that guarantees high-probability state-wise constraint satisfaction for stochastic systems. We demonstrate the effectiveness of our approach by training neural network policies for extensive robot locomotion tasks, where the agent must adhere to various state-wise safety constraints. Our results show that ASCPO significantly outperforms existing methods in handling state-wise constraints across challenging continuous control tasks, highlighting its potential for real-world applications.

The requirements for real-world manipulation tasks are diverse and often conflicting; some tasks require precise motion while others require force compliance; some tasks require avoidance of certain regions, while others require convergence to certain states. Satisfying these varied requirements with a fixed state-action representation and control strategy is challenging, impeding the development of a universal robotic foundation model. In this work, we propose Meta-Control, the first LLM-enabled automatic control synthesis approach that creates customized state representations and control strategies tailored to specific tasks. Our core insight is that a meta-control system can be built to automate the thought process that human experts use to design control systems. Specifically, human experts heavily use a model-based, hierarchical (from abstract to concrete) thought model, then compose various dynamic models and controllers together to form a control system. Meta-Control mimics the thought model and harnesses LLM's extensive control knowledge with Socrates' "art of midwifery" to automate the thought process. Meta-Control stands out for its fully model-based nature, allowing rigorous analysis, generalizability, robustness, efficient parameter tuning, and reliable real-time execution.

Deep reinforcement learning (DRL) has demonstrated impressive performance in many continuous control tasks. However, one major stumbling block to the real-world application of DRL is the lack of safety guarantees. Although DRL agents can statisfy the system safety in expectation through reward shaping, it is quite challenging to design the DRL agent to consistently meet hard constraints (e.g., safety specification) at every time step. On the other hand, existing works in the field of safe control provide guarantees on the persistent satisfaction of hard safety constraints. However, the explicit analytical system dynamics models are required in order to synthesize the safe control, and the dynamics models are typically not accessible in DRL settings. In this paper, we present a model-free safe control algorithm, implicit safe set algorithm, for synthesizing safeguards for DRL agents that will assure provable safety throughout training. The proposed algorithm synthesizes a safety index (also called the barrier certificate) and a subsequent safe control law only by querying a black-box dynamic function (e.g., a digital twin simulator). Moreover, we theoretically prove that the implicit safe set algorithm guarantees finite time convergence to the safe set and forward invariance for both continuous-time and discrete-time systems. We validate the proposed implicit safe set algorithm on the state-of-the-art safety benchmark Safety Gym, where the proposed method achieves zero safety violations and gains 95% 9% cumulative reward compared to state-of-the-art safe DRL methods.

In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily emphasize improvement in expected performance, lacking the ability to control over the worst-case performance outcomes. To address this limitation, we introduce a novel objective function; by optimizing which, it will lead to guaranteed monotonic improvement in the lower bound of near-total performance samples (absolute performance). Considering this groundbreaking theoretical advancement, we then refine this theoretically grounded algorithm through a series of approximations, resulting in a practical solution called Absolute Policy Optimization (APO). Our experiments demonstrate the effectiveness of our approach across challenging continuous control benchmark tasks and extend its applicability to mastering Atari games. Our findings reveal that APO significantly outperforms state-of-the-art policy gradient algorithms, resulting in substantial improvements in both expected performance and worst-case performance.

Ensuring safety of nonlinear systems under model uncertainty and external disturbances is crucial, especially for real-world control tasks. Predictive methods such as robust model predictive control (RMPC) require solving nonconvex optimization problems online, which leads to high computational burden and poor scalability. Reinforcement learning (RL) works well with complex systems, but pays the price of losing rigorous safety guarantee. This paper presents a theoretical framework that bridges the advantages of both RMPC and RL to synthesize safety filters for nonlinear systems with state- and action-dependent uncertainty. We decompose the robust invariant set (RIS) into two parts: a target set that aligns with terminal region design of RMPC, and a reach-avoid set that accounts for the rest of RIS. We propose a policy iteration approach for robust reach-avoid problems and establish its monotone convergence. This method sets the stage for an adversarial actor-critic deep RL algorithm, which simultaneously synthesizes a reach-avoid policy network, a disturbance policy network, and a reach-avoid value network. The learned reach-avoid policy network is utilized to generate nominal trajectories for online verification, which filters potentially unsafe actions that may drive the system into unsafe regions when worst-case disturbances are applied. We formulate a second-order cone programming (SOCP) approach for online verification using system level synthesis, which optimizes for the worst-case reach-avoid value of any possible trajectories. The proposed safety filter requires much lower computational complexity than RMPC and still enjoys persistent robust safety guarantee. The effectiveness of our method is illustrated through a numerical example.

Safety is one of the biggest concerns to applying reinforcement learning (RL) to the physical world. In its core part, it is challenging to ensure RL agents persistently satisfy a hard state constraint without white-box or black-box dynamics models. This paper presents an integrated model learning and safe control framework to safeguard any agent, where its dynamics are learned as Gaussian processes. The proposed theory provides (i) a novel method to construct an offline dataset for model learning that best achieves safety requirements; (ii) a parameterization rule for safety index to ensure the existence of safe control; (iii) a safety guarantee in terms of probabilistic forward invariance when the model is learned using the aforementioned dataset. Simulation results show that our framework guarantees almost zero safety violation on various continuous control tasks.

Control systems often need to satisfy strict safety requirements. Safety index provides a handy way to evaluate the safety level of the system and derive the resulting safe control policies. However, designing safety index functions under control limits is difficult and requires a great amount of expert knowledge. This paper proposes a framework for synthesizing the safety index for general control systems using sum-of-squares programming. Our approach is to show that ensuring the non-emptiness of safe control on the safe set boundary is equivalent to a local manifold positiveness problem. We then prove that this problem is equivalent to sum-of-squares programming via the Positivstellensatz of algebraic geometry. We validate the proposed method on robot arms with different degrees of freedom and ground vehicles. The results show that the synthesized safety index guarantees safety and our method is effective even in high-dimensional robot systems.

Deep reinforcement learning (RL) excels in various control tasks, yet the absence of safety guarantees hampers its real-world applicability. In particular, explorations during learning usually results in safety violations, while the RL agent learns from those mistakes. On the other hand, safe control techniques ensure persistent safety satisfaction but demand strong priors on system dynamics, which is usually hard to obtain in practice. To address these problems, we present Safe Set Guided State-wise Constrained Policy Optimization (S-3PO), a pioneering algorithm generating state-wise safe optimal policies with zero training violations, i.e., learning without mistakes. S-3PO first employs a safety-oriented monitor with black-box dynamics to ensure safe exploration. It then enforces a unique cost for the RL agent to converge to optimal behaviors within safety constraints. S-3PO outperforms existing methods in high-dimensional robotics tasks, managing state-wise constraints with zero training violation. This innovation marks a significant stride towards real-world safe RL deployment.