Designing planners and controllers for contact-rich manipulation is extremely challenging as contact violates the smoothness conditions that many gradient-based controller synthesis tools assume. Contact smoothing approximates a non-smooth system with a smooth one, allowing one to use these synthesis tools more effectively. However, applying classical control synthesis methods to smoothed contact dynamics remains relatively under-explored. This paper analyzes the efficacy of linear controller synthesis using differential simulators based on contact smoothing. We introduce natural baselines for leveraging contact smoothing to compute (a) open-loop plans robust to uncertain conditions and/or dynamics, and (b) feedback gains to stabilize around open-loop plans. Using robotic bimanual whole-body manipulation as a testbed, we perform extensive empirical experiments on over 300 trajectories and analyze why LQR seems insufficient for stabilizing contact-rich plans.

Model predictive control is a powerful tool to generate complex motions for robots. However, it often requires solving non-convex problems online to produce rich behaviors, which is computationally expensive and not always practical in real time. Additionally, direct integration of high dimensional sensor data (e.g. RGB-D images) in the feedback loop is challenging with current state-space methods. This paper aims to address both issues. It introduces a model predictive control scheme, where a neural network constantly updates the cost function of a quadratic program based on sensory inputs, aiming to minimize a general non-convex task loss without solving a non-convex problem online. By updating the cost, the robot is able to adapt to changes in the environment directly from sensor measurement without requiring a new cost design. Furthermore, since the quadratic program can be solved efficiently with hard constraints, a safe deployment on the robot is ensured. Experiments with a wide variety of reaching tasks on an industrial robot manipulator demonstrate that our method can efficiently solve complex non-convex problems with high-dimensional visual sensory inputs, while still being robust to external disturbances.

This paper presents an efficient approach to object manipulation planning using Monte Carlo Tree Search (MCTS) to find contact sequences and an efficient ADMM-based trajectory optimization algorithm to evaluate the dynamic feasibility of candidate contact sequences. To accelerate MCTS, we propose a methodology to learn a goal-conditioned policy-value network and a feasibility classifier to direct the search towards promising nodes. Further, manipulation-specific heuristics enable to drastically reduce the search space. Systematic object manipulation experiments in a physics simulator and on real hardware demonstrate the efficiency of our approach. In particular, our approach scales favorably for long manipulation sequences thanks to the learned policy-value network, significantly improving planning success rate. All source code including the baseline can be found at https://hzhu.io/contact-mcts.

Real-world applications require light-weight, energy-efficient, fully autonomous robots. Yet, increasing autonomy is oftentimes synonymous with escalating computational requirements. It might thus be desirable to offload intensive computation-not only sensing and planning, but also low-level whole-body control-to remote servers in order to reduce on-board computational needs. Fifth Generation (5G) wireless cellular technology, with its low latency and high bandwidth capabilities, has the potential to unlock cloud-based high performance control of complex robots. However, state-of-the-art control algorithms for legged robots can only tolerate very low control delays, which even ultra-low latency 5G edge computing can sometimes fail to achieve. In this work, we investigate the problem of cloud-based whole-body control of legged robots over a 5G link. We propose a novel approach that consists of a standard optimization-based controller on the network edge and a local linear, approximately optimal controller that significantly reduces on-board computational needs while increasing robustness to delay and possible loss of communication. Simulation experiments on humanoid balancing and walking tasks that includes a realistic 5G communication model demonstrate significant improvement of the reliability of robot locomotion under jitter and delays likely to be experienced in 5G wireless links.

Humans are error-prone in the presence of multiple similar tasks. While Human-Robot Collaboration (HRC) brings the advantage of combining the superiority of both humans and robots in their respective talents, it also requires the robot to communicate the task goal clearly to the human collaborator. We formalize such problems in interactive assembly tasks with hidden goal Markov decision processes (HGMDPs) to enable the symbiosis of human intention recognition and robot intention expression. In order to avoid the prohibitive computational requirements, we provide a myopic heuristic along with a feature-based state abstraction method for assembly tasks to approximate the solution of the resulting HGMDP. A user study with human subjects in round-based LEGO assembly tasks shows that our algorithm improves HRC and helps the human collaborators when the task goal is unclear to them.