Hongpeng Cao

Capturing latent variations ("contexts") is key to deploying reinforcement-learning (RL) agents beyond their training regime. We recast context-based RL as a dual inference-control problem and formally characterize two properties and their hierarchy: observation sufficiency (preserving all predictive information) and control sufficiency (retaining decision-making relevant information). Exploiting this dichotomy, we derive a contextual evidence lower bound(ELBO)-style objective that cleanly separates representation learning from policy learning and optimizes it with Bottlenecked Contextual Policy Optimization (BCPO), an algorithm that places a variational information-bottleneck encoder in front of any off-policy policy learner. On standard continuous-control benchmarks with shifting physical parameters, BCPO matches or surpasses other baselines while using fewer samples and retaining performance far outside the training regime. The framework unifies theory, diagnostics, and practice for context-based RL.

This paper proposes the runtime learning machine for safety-critical learning-enabled cyber-physical systems (CPS). The learning machine has three interactive components: a high-performance (HP)-Student, a high-assurance (HA)-Teacher, and a Coordinator. The HP-Student is a high-performance but not fully verified Phy-DRL (physics-regulated deep reinforcement learning) agent that performs runtime learning in real CPS, using real-time sensor data from real-time physical environments. On the other hand, HA-Teacher is a verified but simplified design, focusing on safety-critical functions only. As a complementary, HA-Teacher's novelty lies in real-time patch for two missions: i) correcting unsafe learning of HP-Student, and ii) backing up safety. The Coordinator manages the interaction between HP-Student and HA-Teacher. Powered by the three interactive components, the runtime learning machine notably features i) assuring lifetime safety (i.e., safety guarantee in any runtime learning stage), ii) tolerating unknown unknowns, iii) addressing Sim2Real gap, and iv) automatic hierarchy learning (i.e., safety-first learning, and then high-performance learning). Experiments involving a cart-pole system and two quadruped robots, as well as comparisons with state-of-the-art safe DRL, fault-tolerant DRL, and approaches for addressing Sim2Real gap, demonstrate the learning machine's effectiveness and unique features.

Real-world accidents in learning-enabled CPS frequently occur in challenging corner cases. During the training of deep reinforcement learning (DRL) policy, the standard setup for training conditions is either fixed at a single initial condition or uniformly sampled from the admissible state space. This setup often overlooks the challenging but safety-critical corner cases. To bridge this gap, this paper proposes a physics-model-guided worst-case sampling strategy for training safe policies that can handle safety-critical cases toward guaranteed safety. Furthermore, we integrate the proposed worst-case sampling strategy into the physics-regulated deep reinforcement learning (Phy-DRL) framework to build a more data-efficient and safe learning algorithm for safety-critical CPS. We validate the proposed training strategy with Phy-DRL through extensive experiments on a simulated cart-pole system, a 2D quadrotor, a simulated and a real quadruped robot, showing remarkably improved sampling efficiency to learn more robust safe policies.

6D pose recognition has been a crucial factor in the success of robotic grasping, and recent deep learning based approaches have achieved remarkable results on benchmarks. However, their generalization capabilities in real-world applications remain unclear. To overcome this gap, we introduce 6IMPOSE, a novel framework for sim-to-real data generation and 6D pose estimation. 6IMPOSE consists of four modules: First, a data generation pipeline that employs the 3D software suite Blender to create synthetic RGBD image datasets with 6D pose annotations. Second, an annotated RGBD dataset of five household objects was generated using the proposed pipeline. Third, a real-time two-stage 6D pose estimation approach that integrates the object detector YOLO-V4 and a streamlined, real-time version of the 6D pose estimation algorithm PVN3D optimized for time-sensitive robotics applications. Fourth, a codebase designed to facilitate the integration of the vision system into a robotic grasping experiment. Our approach demonstrates the efficient generation of large amounts of photo-realistic RGBD images and the successful transfer of the trained inference model to robotic grasping experiments, achieving an overall success rate of 87% in grasping five different household objects from cluttered backgrounds under varying lighting conditions. This is made possible by fine-tuning data generation and domain randomization techniques and optimizing the inference pipeline, overcoming the generalization and performance shortcomings of the original PVN3D algorithm. Finally, we make the code, synthetic dataset, and all the pre-trained models available on GitHub.

Deep reinforcement learning (DRL) has achieved tremendous success in many complex decision-making tasks of autonomous systems with high-dimensional state and/or action spaces. However, the safety and stability still remain major concerns that hinder the applications of DRL to safety-critical autonomous systems. To address the concerns, we proposed the Phy-DRL: a physical deep reinforcement learning framework. The Phy-DRL is novel in two architectural designs: i) Lyapunov-like reward, and ii) residual control (i.e., integration of physics-model-based control and data-driven control). The concurrent physical reward and residual control empower the Phy-DRL the (mathematically) provable safety and stability guarantees. Through experiments on the inverted pendulum, we show that the Phy-DRL features guaranteed safety and stability and enhanced robustness, while offering remarkably accelerated training and enlarged reward.

6D pose recognition has been a crucial factor in the success of robotic grasping, and recent deep learning based approaches have achieved remarkable results on benchmarks. However, their generalization capabilities in real-world applications remain unclear. To overcome this gap, we introduce 6IMPOSE, a novel framework for sim-to-real data generation and 6D pose estimation. 6IMPOSE consists of four modules: First, a data generation pipeline that employs the 3D software suite Blender to create synthetic RGBD image datasets with 6D pose annotations. Second, an annotated RGBD dataset of five household objects generated using the proposed pipeline. Third, a real-time two-stage 6D pose estimation approach that integrates the object detector YOLO-V4 and a streamlined, real-time version of the 6D pose estimation algorithm PVN3D optimized for time-sensitive robotics applications. Fourth, a codebase designed to facilitate the integration of the vision system into a robotic grasping experiment. Our approach demonstrates the efficient generation of large amounts of photo-realistic RGBD images and the successful transfer of the trained inference model to robotic grasping experiments, achieving an overall success rate of 87% in grasping five different household objects from cluttered backgrounds under varying lighting conditions. This is made possible by the fine-tuning of data generation and domain randomization techniques, and the optimization of the inference pipeline, overcoming the generalization and performance shortcomings of the original PVN3D algorithm. Finally, we make the code, synthetic dataset, and all the pretrained models available on Github.

Gear assembly is an essential but challenging task in industrial automation. This paper presents a novel two-stage approach for achieving high-precision and flexible gear assembly. The proposed approach integrates YOLO to coarsely localize the workpiece in a searching phase and deep reinforcement learning (DRL) to complete the insertion. Specifically, DRL addresses the challenge of partial visibility when the on-wrist camera is too close to the workpiece. Additionally, force feedback is used to smoothly transit the process from the first phase to the second phase. To reduce the data collection effort for training deep neural networks, we use synthetic RGB images for training YOLO and construct an offline interaction environment leveraging sampled real-world data for training DRL agents. We evaluate the proposed approach in a gear assembly experiment with a precision tolerance of 0.3mm. The results show that our method can robustly and efficiently complete searching and insertion from arbitrary positions within an average of 15 seconds.

Deep reinforcement learning (DRL) is a promising approach to solve complex control tasks by learning policies through interactions with the environment. However, the training of DRL policies requires large amounts of training experiences, making it impractical to learn the policy directly on physical systems. Sim-to-real approaches leverage simulations to pretrain DRL policies and then deploy them in the real world. Unfortunately, the direct real-world deployment of pretrained policies usually suffers from performance deterioration due to the different dynamics, known as the reality gap. Recent sim-to-real methods, such as domain randomization and domain adaptation, focus on improving the robustness of the pretrained agents. Nevertheless, the simulation-trained policies often need to be tuned with real-world data to reach optimal performance, which is challenging due to the high cost of real-world samples. This work proposes a distributed cloud-edge architecture to train DRL agents in the real world in real-time. In the architecture, the inference and training are assigned to the edge and cloud, separating the real-time control loop from the computationally expensive training loop. To overcome the reality gap, our architecture exploits sim-to-real transfer strategies to continue the training of simulation-pretrained agents on a physical system. We demonstrate its applicability on a physical inverted-pendulum control system, analyzing critical parameters. The real-world experiments show that our architecture can adapt the pretrained DRL agents to unseen dynamics consistently and efficiently.