A good representation of a large, complex mobile robot workspace must be space-efficient yet capable of encoding relevant geometric details. When exploring unknown environments, it needs to be updatable incrementally in an online fashion. We introduce HIO-SDF, a new method that represents the environment as a Signed Distance Field (SDF). State of the art representations of SDFs are based on either neural networks or voxel grids. Neural networks are capable of representing the SDF continuously. However, they are hard to update incrementally as neural networks tend to forget previously observed parts of the environment unless an extensive sensor history is stored for training. Voxel-based representations do not have this problem but they are not space-efficient especially in large environments with fine details. HIO-SDF combines the advantages of these representations using a hierarchical approach which employs a coarse voxel grid that captures the observed parts of the environment together with high-resolution local information to train a neural network. HIO-SDF achieves a 46% lower mean global SDF error across all test scenes than a state of the art continuous representation, and a 30% lower error than a discrete representation at the same resolution as our coarse global SDF grid. Videos and code are available at: https://samsunglabs.github.io/HIO-SDF-project-page/

We introduce Reactive Action and Motion Planner (RAMP), which combines the strengths of sampling-based and reactive approaches for motion planning. In essence, RAMP is a hierarchical approach where a novel variant of a Model Predictive Path Integral (MPPI) controller is used to generate trajectories which are then followed asynchronously by a local vector field controller. We demonstrate, in the context of a table clearing application, that RAMP can rapidly find paths in the robot's configuration space, satisfy task and robot-specific constraints, and provide safety by reacting to static or dynamically moving obstacles. RAMP achieves superior performance through a number of key innovations: we use Signed Distance Function (SDF) representations directly from the robot configuration space, both for collision checking and reactive control. The use of SDFs allows for a smoother definition of collision cost when planning for a trajectory, and is critical in ensuring safety while following trajectories. In addition, we introduce a novel variant of MPPI which, combined with the safety guarantees of the vector field trajectory follower, performs incremental real-time global trajectory planning. Simulation results establish that our method can generate paths that are comparable to traditional and state-of-the-art approaches in terms of total trajectory length while being up to 30 times faster. Real-world experiments demonstrate the safety and effectiveness of our approach in challenging table clearing scenarios. Videos and code are available at: https://samsunglabs.github.io/RAMP-project-page/

In this paper we address mobile manipulation planning problems in the presence of sensing and environmental uncertainty. In particular, we consider mobile sensing manipulators operating in environments with unknown geometry and uncertain movable objects, while being responsible for accomplishing tasks requiring grasping and releasing objects in a logical fashion. Existing algorithms either do not scale well or neglect sensing and/or environmental uncertainty. To face these challenges, we propose a hybrid control architecture, where a symbolic controller generates high-level manipulation commands (e.g., grasp an object) based on environmental feedback, an informative planner designs paths to actively decrease the uncertainty of objects of interest, and a continuous reactive controller tracks the sparse waypoints comprising the informative paths while avoiding a priori unknown obstacles. The overall architecture can handle environmental and sensing uncertainty online, as the robot explores its workspace. Using numerical simulations, we show that the proposed architecture can handle tasks of increased complexity while responding to unanticipated adverse configurations.

We describe a task and motion planning architecture for highly dynamic systems that combines a domain-independent sampling-based deliberative planning algorithm with a global reactive planner. We leverage the recent development of a reactive, vector field planner that provides guarantees of reachability to large regions of the environment even in the face of unknown or unforeseen obstacles. The reachability guarantees can be formalized using contracts that allow a deliberative planner to reason purely in terms of those contracts and synthesize a plan by choosing a sequence of reactive behaviors and their target configurations, without evaluating specific motion plans between targets. This reduces both the search depth at which plans will be found, and the number of samples required to ensure a plan exists, while crucially preserving correctness guarantees. The result is reduced computational cost of synthesizing plans, and increased robustness of generated plans to actuator noise, model misspecification, or unknown obstacles. Simulation studies show that our hierarchical planning and execution architecture can solve complex navigation and rearrangement tasks, even when faced with narrow passageways or incomplete world information.

Complex manipulation tasks, such as rearrangement planning of numerous objects, are combinatorially hard problems. Existing algorithms either do not scale well or assume a great deal of prior knowledge about the environment, and few offer any rigorous guarantees. In this paper, we propose a novel hybrid control architecture for achieving such tasks with mobile manipulators. On the discrete side, we enrich a temporal logic specification with mobile manipulation primitives such as moving to a point, and grasping or moving an object. Such specifications are translated to an automaton representation, which orchestrates the physical grounding of the task to mobility or manipulation controllers. The grounding from the discrete to the continuous reactive controller is online and can respond to the discovery of unknown obstacles or decide to push out of the way movable objects that prohibit task accomplishment. Despite the problem complexity, we prove that, under specific conditions, our architecture enjoys provable completeness on the discrete side, provable termination on the continuous side, and avoids all obstacles in the environment. Simulations illustrate the efficiency of our architecture that can handle tasks of increased complexity while also responding to unknown obstacles or unanticipated adverse configurations.

In this article, we physically demonstrate a reactive sensorimotor architecture for mobile robots whose behaviors are generated by motivation dynamics. Motivation dynamics uses a continuous dynamical system to reactively compose low-level control vector fields using valuation functions that capture the potentially competing influences of external stimuli relative to the system's own internal state. We show that motivation dynamics naturally accommodates external stimuli through standard signal processing tools, and can effectively encode a repetitive higher level task by composing several low-level controllers to achieve a limit cycle in which the robot repeatedly navigates toward two alternatively valuable goal locations in a commensurately alternating order. We show that these behaviors are robust to perturbations, including imperfect models of robot kinematics, sensor noise, and disturbances, resulting from the need to traverse difficult terrain. We argue that motivation dynamics can provide a useful alternative to controllers based on hybrid automata in situations where the control operates at a low level close to the physical hardware.

This paper considers the problem of completing assemblies of passive objects in nonconvex environments, cluttered with convex obstacles of unknown position, shape and size that satisfy a specific separation assumption. A differential drive robot equipped with a gripper and a LIDAR sensor, capable of perceiving its environment only locally, is used to position the passive objects in a desired configuration. The method combines the virtues of a deliberative planner generating high-level, symbolic commands, with the formal guarantees of convergence and obstacle avoidance of a reactive planner that requires little onboard computation and is used online. The validity of the proposed method is verified both with formal proofs and numerical simulations.

We demonstrate the physical rearrangement of wheeled stools in a moderately cluttered indoor environment by a quadrupedal robot that autonomously achieves a user's desired configuration. The robot's behaviors are planned and executed by a three layer hierarchical architecture consisting of: an offline symbolic task and motion planner; a reactive layer that tracks the reference output of the deliberative layer and avoids unanticipated obstacles sensed online; and a gait layer that realizes the abstract unicycle commands from the reactive module through appropriately coordinated joint level torque feedback loops. This work also extends prior formal results about the reactive layer to a broad class of nonconvex obstacles. Our design is verified both by formal proofs as well as empirical demonstration of various assembly tasks.

While legged locomotion is a rapidly advancing area in robotics, several issues regarding the performance of such robots on deformable ground are still open. In this paper, we generate a pronking gait on a quadruped robot using a controller, which takes into account the effects of ground deformation. The controller, initially developed for monopods, is modified appropriately to operate for quadrupeds. The robot uses a reaction wheel to retain a desired body pitch. The dynamic models of leg motor drivetrains and of the reaction wheel are incorporated and their importance in the design of legged robots is highlighted. Simulation results show good performance in reaching commanded apex heights and forward velocities when traversing various deformable terrains, demonstrating that the developed controller is quite promising.

Terrain compliance is a critical parameter for the performance of legged locomotion. In this work, a single actuator monopod robot hopping on rough compliant terrain is considered. Based on our controller for flat compliant terrains, this paper introduces the necessary modifications, which allow the robot to tackle the disturbance of small inclinations. Using the developed method, the robot is examined on its performance to traverse rough terrains, while maintaining the goals of reaching a desired height and forward velocity. As the increased compliance and inclination alter the energy requirements from the controller actuator, the Cost of Transport (CoT) index for a number of scenarios is studied. The correlation between terrain parameters and the CoT is presented, and useful conclusions, which can aid the understanding of the behavior of legged robots in realistic terrains are extracted.

Legged locomotion is a rapidly advancing area in robotics, yet still a large number of open questions exist. This work focuses on the foot-terrain interaction and its effect on the motion of a one-legged system. This interaction is usually tackled by disregarding some of the effects of ground deformation like permanent deformation and compaction. Inspired by other areas of engineering, an impact dynamics model is developed, allowing a more thorough study of the behavior during fast dynamic walking. This approach can be regarded as a viscoplastic one. The monopod controller presented in previous work is extended to cope with deformable terrains, based on energy dissipation considerations, without requiring the knowledge of the ground parameters. Simulation results prove the validity of the theory presented.